Topaz Photo

Hello everyone! This release includes the following changes:

• the amazing new Wonder 3.5 model
• unlimited output size for Neuroserver models
• new camera support
• metadata and optional watermarking for compliance with California AI Transparency Act
• many bug fixes. You can find the installer links and the full changelog below for this version of Topaz Photo. For any issues, make sure to send us an email to support@topazlabs.com v1.7.0 Released August 25th, 2026 Windows: Download Snapdragon: Download Apple Silicon Mac: Download Intel Mac: Download WONDER 3.5 is here! Wonder 3.5 builds on Wonder 3 with higher detail, greater precision, and more natural realism. Same generative upscaling model you already use, improved across the board. You get finer detail with fewer repetitive patterns, better handling of visual noise, and stronger results on the heavily degraded and compressed images that are hardest to recover. The biggest improvements show up on low-resolution and compressed photos, creating clearer detail and sharper text, and on structured graphics like tables and charts, where it’s noticeably more precise. It still holds strong across portraits, landscapes, wildlife, and complex textures. What 3.5 improves over Wonder 3:
• Higher-quality results with increased detail and improved realism
• More transformative enhancement for low-resolution and compressed photos, with better detail and text clarity
• Fewer repetitive patterns and improved handling of visual noise Despite these improvements, the processing speed is exactly the same. All gains, no losses! As usual, Wonder 3.5 comes with both local and cloud render. Cloud render has a 100MP output limit. Local render is now unrestricted for output size! No More Limits — NeuroServer Local Models Now Run Unrestricted Last version, NeuroServer received significant local processing speed improvements - processing was made 2x faster on Mac and up to 4x faster on Windows systems with 8GB/12GB VRAM GPUs. In this latest version, we’ve now removed the previous processing limit for NeuroServer models when rendering locally (was at 192MP). If your machine meets the requirements, you can now upscale to larger output sizes locally without the previous cap. This means that the following Neuroserver models can work with images of all sizes and formats, including high quality files such as TIFs, RAWs, PNGs, or JPG XLs. Combined, these changes make local processing both faster and less restricted for large images, high-resolution outputs and batches. New Camera Support We’ve added highly requested RAW support for 3 new cameras, continuing our effort to ensure your files import and process correctly from the start. If you shoot with any of the cameras below, you should now be able to open and work with your images in Topaz Photo without extra conversion steps:
• Sony A7RV
• Sony A7RVI
• Sony Alpha 9 III Please try loading RAW files from these cameras and let us know if you run into any issues with import, color, or processing. Your feedback will helps us validate and finalize camera support for these. Metadata and Optional Watermarking In accordance with the California AI Transparency Act (CAITA), we’re adding the following changes to Topaz Photo to meet the requirements:

Embedded metadata, called Content Credentials, noting that an image was processed with our application. Any image can be checked at the inspect tool to verify this metadata.

Optional watermarking for anyone who wants to use it. Watermarking is default off, to turn it on go to the Preferences > Export menu. The watermark looks like this, in the bottom right corner of your image:

We’ve updated the EULA to reflect these changes. Image output quality will stay the same. The only visual indicator will be the watermark if you turn it on. Find details about the CAITA here. Known Issues

• The new paywall screen gets cropped off at the bottom when the app window is at its minimum size, hiding the “Switch account” button Changelog
• Added Wonder 3.5
• Remove restriction on Neuroserver output size (was 192MP, now up to max output size)
• Added new camera support: Sony A7RV, Sony A7RVI, Sony Alpha 9 III
• Added new watermark options now available in the export settings
• Expanded metadata support
• Super Focus v3 works on RAW images
• Fixed an issue where AI model installation could fail for users without admin permissions
• Refreshed the paywall design
• Fixed an error preventing a model from downloading in Portrait mode on Windows
• Fixed a crash that could occur when running the Auto-pilot across multiple files at once
• Fixed a black square outline artifact appearing with Recover faces 3 when using cloud processing Lingyu Kong Technical Product Manager Image AI 12 posts - 9 participants Read full topic

Hello everyone! Today we have a patch release for Topaz Photo with a large list of fixes. We also shipped a NeuroServer update that brings 2x faster processing on Mac, and up to 4x faster processing on low VRAM GPUs (8GB to 12GB) for Windows! v1.6.1 Released June 11th, 2026 Windows: Download Snapdragon: Download Apple Silicon Mac: Download Intel Mac: Download Neuroserver Speed Improvements for Mac and Windows In this release are many improvements to NeuroServer which speeds up both Mac and Windows processing in different ways. Overall, NeuroServer runs efficiently compared to previous versions, which benefits all NeuroServer-based models: Wonder 2, Wonder 3, Super Focus v3, Denoise Max, and Recover Faces 3. Mac On Mac, two things changed. First, NeuroServer initialization and model loading are significantly faster. The first run after installing should start up noticeably quicker, and subsequent runs load faster too. Second, processing now uses both the GPU and Neural Engine together. Combined, Mac processing is 2x faster across all NeuroServer models. Windows On GPUs that meet the minimum VRAM requirements (8GB and 12GB cards) NeuroServer was running inefficently due to memory usage. We have reduced requirements to allow faster image processing on these devices which were bottlenecked by memory. For 8GB and 12GB VRAM GPUs, the speed improvement is up to 4x. in our testing with an NVIDIA 4060 Laptop GPU with 8GB VRAM, we upscaled a 24MP image to 96MP (2x upscale) with the following results. Note that devices with more GPU have lower improvement due to no memory bottleneck in processing.

• 1982s (33m) processing time on v1.6.0
• 450s (7.5m) processing time on v1.6.1, a 4x increase If you’ve been avoiding these models for larger images or batches because of processing time, this update changes that calculation. Changelog
• Add color correction to High Fidelity 3 to prevent color shift
• Limit output to 192MP for Wonder 2 and Wonder 3 local render due to NeuroServer limitations
• Remove unnecesary warning when using Wonder with Raw files
• Block NeuroServer local processing for devices below minimum GPU requirements
• Block Face Recovery 3 when generative AI is disabled in settings
• Fix resolution settings not applying properly from upscale menu
• Fix RAW denoise not adding in batch processing when images are not loaded and analyzed
• Fix filmstrip tooltip information
• Fix Denoise MAX having no way to reprocess and change strength
• Fix processing deselected faces in Recover Faces when another enhancement is added
• Fix face recovery default sometimes selecting 0 faces
• Fix enterprise seat claiming
• Fix window controls on top left not centered on Mac Lingyu Kong Technical Product Manager Image AI 142 posts - 38 participants Read full topic

Hello everyone! A new release for Topaz Photo, with two new models and a significant speed improvement for many NeuroServer-based models.

• Recover Faces 3 — Portrait Quality Face Recovery
• Sharpen - Noise-Aware — Sharpen Detail, Not Noise
• NeuroServer Model Speed Improvements — Over 300% Faster You can find the installer links and the full changelog below for this version of Topaz Photo. For any issues, make sure to send us an email to support@topazlabs.com v1.6.0 Released May 13th, 2026 Windows: Download Snapdragon: Download Apple Silicon Mac: Download Intel Mac: Download Recover Faces 3 — Portrait Quality Face Recovery Recover Faces 2 had two problems that limited how useful it was for many images. The first was a hard size limit. Recover Faces 2 has a maximum output size of 512x512 pixels. Faces larger than that are forced to the smaller size, losing detail and sharpness. Faces that needed recovery would look smooth and out of place when compared to the rest of the image. Our recommendation was to avoid using it entirely in these situations. The second was dot artifacts that appeared at high strength levels, exactly when you’d need strong recovery the most. On blurry or low quality faces, a strong face recovery is needed, but artifacts would make the result unusable. Recover Faces 3 fixes both these issues to expand when the enhancement can be used. The size limit is gone. Recover Faces 3 sharpens and recovers soft detail on faces of any size, producing sharp, portrait-quality output regardless of how large the face is in the frame. This image has a large face with soft details. There is room for improvement, but the existing Recover Faces 2 model would not create an acceptable output. Using Recover Faces 2, the freckles are reduced significantly. The eyes are softened instead of improved. Eyebrow hairs are blended together as well. Meanwhile, Recover Faces 3 is able to sharpen the eyes, improve the skin, and enhance the eyebrows too. It’s far better suited for high quality outputs. The dot artifact issue is resolved. You can push strength as high as the image calls for without worrying about it. For low quality or heavily degraded faces, that means the model recovers those faces with high quality output. The new model is a generative recover faces model that processes each face separately. Each additional face selected will increase processing time. For example, 4 similarly sized faces will take 4x the time compared to 1 face of the same size. For faces already with decent quality and below the 512x512 pixel limit, Recover Faces 2 will still do the job and process faster. For large faces, blurry faces, or anything degraded enough that Recover Faces 2 struggled, 3 is the better starting point. and the quality difference is worth the extra processing time. Recover Faces 3 runs on NeuroServer and processes locally on NVIDIA, AMD, and Apple Silicon (macOS 14 or later). Cloud render is available for unsupported hardware, up to a maximum output size of 100MP. Due to the lower quality of the older model, we are sunsetting Recover Faces 1. Sharpen - Noise-Aware — Sharpen Detail, Not Noise Photographers working on location don’t get to control their conditions. For wildlife, portrait, sports, and other types of photography you may be forced to shoot in low light, fast moments. The noise and grain in those captured moments is part of what makes your images come alive. Every sharpening model we’ve shipped until now treats that texture as a problem. Sharpening will enhance noise or grain to a distracting level, which means it must be removed before sharpening the underlying detail. In doing so you lose the character of that moment. Noise-aware is built for these situations. You can find it in the Sharpen enhancement. It’s the first sharpening model that separates noise from detail before touching anything. It reads the noise structure in the image and sharpens only the underlying detail in the captured scene. The result is a sharper image with noise and grain intact. It still looks like the image you shot, with the details you care about enhanced. Take this wildlife image for example. Using existing sharpening models on this image enhances the noise, instead of sharpening the main subject details. Looking at the ear and the fur on the face, it’s clear that the digital noise now looks like grain. With the noise-aware model, we can now sharpen without touching the noise. The fur details are noticeably clearer without creating artifacts. In this nighttime go karting picture, sharpening the image with existing sharpen models boosts the noise to the point of distracting from the driver and kart. Noise-aware works on the layer under the noise, bringing the subject in focus without creating artifacts. Noise-aware is a new addition to the sharpening model lineup, not a replacement for existing models. If your images are clean, the existing sharpening models remain the right tool. If you shoot in conditions where texture and noise are part of the image, this is the model that’s been missing. NeuroServer Model Speed Improvements — Over 300% Faster NeuroServer-based models are now significantly faster. We reduced the model load time and increased processing speed for Wonder 3, Super Focus v3, and Denoise Max. Testing with a NVIDIA 3080 at 20MP output, we saw a speed increase of 330%. For larger images and faster GPUs, the speed increase is possibly even larger. If you’ve been putting off images and batches because of processing time, this update will enable you to use these models more. Recover Faces 3 benefits from the same improvements. The version shipping today already includes the speed gains, so there’s nothing extra to enable. Hopefully this encourages more usage for these models with images that need the extra push. Known Issues
• Recover faces 3 intermittent out of GPU memory error with 8GB VRAM. Will have a fix in next patch. Changelog
• Add Face Recovery v3 through Neuroserver for NVIDIA, AMD, and Apple Silicon devices
• Add Face Recovery v3 cloud render
• Add Sharpen - Noise-aware model
• Update Upscale - High fidelity v3 model
• Update NeuroServer to speed up Wonder 3, Super Focus v3, Denoise Max, Face Recovery v3
• Fix crash with face parse model in image analysis
• Fix Remove v2 error running model on some devices
• Fix Remove v2 and Recover v3 grey output on Windows devices with foreign locales Lingyu Kong Technical Product Manager Image AI 133 posts - 28 participants Read full topic

Hello everyone! Here is v1.5.1, a hotfix for issues reported in the previous release. v1.5.1 Released April 27th, 2026 Windows: Download Snapdragon: Download Apple Silicon Mac: Download Intel Mac: Download Known Issues

• Black padding on cloud renders with Wonder 3 when a decimal scale is used. Will be fixed on cloud without requiring update.
• Super Focus v3 not running on Win ARM. Support will be added later. Changelog
• Improvement to Wonder 3 local quality
• Improvement to Denoise Max local quality
• Improvement to Super Focus v3 local quality
• Fix for Super Focus v2 failing due to a missing file on Windows
• Fix for Wonder 2 failing to run locally on Windows
• Fix for Wonder 3 cloud render failing due to an invalid upscale factor
• Fix for Wonder 3 on Windows always processing at the same strength regardless of the setting
• Fix for Denoise Max throwing an error on Windows due to a log file access issue
• Fix for image analysis stalling on Windows ARM devices
• Fix for image analysis failing on Intel Xeon, AMD Threadripper, and similar CPUs
• Fix for AI models not being downloaded during Wonder 3 installation on Windows
• Fix for the installer getting stuck when extracting Wonder 2 model files
• Disabled the Mac x86 installer option for Apple Silicon devices to prevent incorrect installations Hello everyone! A new release for Topaz Photo, with 4 new models that we are very excited for. Each is an improvement on our core functionality: denoise, sharpen, upscaling, and recovery. Three of these models also run on our Neuroserver technology which allows NVIDIA, AMD, and Apple Silicon devices to run large models locally.
• High Fidelity v3 — Better Detail, Fewer Artifacts
• Wonder 3 — Smarter Recovery Across More Images
• Denoise Max — Generative Denoising for Extreme Noise
• Super Focus v3 — Natural Results for Extreme Blur You can find the installer links and the full changelog below for this version of Topaz Photo. For any issues, make sure to send us an email to support@topazlabs.com v1.5.0 Released April 25th, 2026 Windows: Download Snapdragon: Download Apple Silicon Mac: Download Intel Mac: Download High Fidelity v3 — Better Detail, Fewer Artifacts High Fidelity is designed for images that are already in good shape. Where other models focus on recovery, High Fidelity’s job is to enhance what’s already there: sharper detail, cleaner textures, and upscaled output that holds up at full resolution. v3 raises the bar on all of these, and fixes the cases where v2 fell short. The core change in v3 is a two-part architecture. Before upscaling begins, an analysis model reads the image, both as a whole and at the block level, to build a detailed understanding of its content. The upscaling model then uses that context to produce output that stays true to the original while generating realistic detail even at larger upscale values. Earlier models would struggle here, as small structures get magnified significantly and realistic detail becomes much harder to maintain. This approach also meaningfully reduces AI artifacts. Two areas we’re especially happy with: natural scenes and skin. Leaves, grass, and similar patterns used to come out repetitive and visibly generated. v3 produces realistic variation. Skin textures, which previously came out either too smooth or too harsh, now retain their natural softness. Beyond artifact reduction, v3 is better at preserving and enhancing textures that are already present in the image. Rather than softening fine detail during upscaling, it sharpens it further, producing a crispness that previous High Fidelity models couldn’t match. High Fidelity v3 is best suited for images that are already high resolution and clearly detailed. Raw files and images above 6MP are ideal candidates. If the source image has strong existing detail, v3 will enhance it further rather than approximate it. For lower resolution or lower quality images, Wonder 3 is the better starting point. We want to hear how it performs on your images, especially on subjects where v2 produced repetitive textures or visible artifacts. Drop your results and feedback in this thread. Wonder 3 — Smarter Recovery Across More Images Wonder 2 set a high bar for general enhancement, but it was not yet at the level we were hoping for recovery. Low detail images, whether blurry, soft focus, or false resolution, saw limited improvements after processing, hitting the limits of what Wonder 2 could handle. Where Wonder 1 may have over-processed images and made them look artificial, it felt like Wonder 2 was not doing enough to improve images. It fell short, so we continued improving it to build the next version. We tested Wonder 3 and quickly found it to be an extremely capable model. It handles images of all sizes and quality. The low quality images that Wonder 2 did not improve enough were easily recovered with Wonder 3, with an emphasis on realism. The new model produces high quality details that previous Wonder models struggled with. Wonder 3 handles difficult false resolution cases extremely well with no extra controls needed. You get better results on a wider range of images without having to intervene. On this portrait, the skin and hair textures are photorealistic. Usually, AI models create smooth skin and hair with repetitive structure. Here, the hair seems to weave naturally around itself and fall down as expected. The skin textures are also imperfect as you would expect. Here’s another example with wildlife imagery. The eyes and feathers where we focus our attention is sharp. The feathers have a blend of softness and detail for a convincing result. The model has two controls. Scale sets your target output size. Enhancement strength controls how generative the model is, giving you more powerful recovery when the image calls for it. Strength is paired with our image detail auto detection: when a low detail image is detected, strength is set automatically to produce the best result. For most images you won’t need to touch it. Wonder 3 runs on Neuroserver which processes locally for NVIDIA, AMD, and Apple Silicon devices, just like Wonder 2 and other Neuroserver based models. For users with other hardware (Intel Mac, Intel GPU) or slow GPU processing, cloud render is available up to a maximum of 100MP in size. We want to hear how it performs on your images, especially at 1x and 2x and on images that have given Wonder 2 trouble in the past. Drop your results and feedback in this thread. Denoise Max — Generative Denoising for Extreme Noise Our existing denoise models handle low and medium noise well. But at the high end of the noise spectrum, results can get patchy, and even a technically clean image can come out looking soft. That softness isn’t a processing artifact, instead it’s missing information that the model is not able to fill in. Heavy noise is part of the image, and it buries the detail that was there in the original scene. Once that detail is obscured, a standard denoise pass is unable to recover the hidden information hidden. For this high noise example, the Denoise - Normal model is not powerful enough to remove the noise. The Denoise - Extreme model cleans up noise but is not able to recover the face or clothes at high quality. Only Denoise Max can produce a detailed and clean output. Denoise Max is our first generative denoising model, built for extreme denoising and detail recovery. It uses the full context of the image to reconstruct detail that noise has hidden rather than simply filtering noise away. The result is a clean image with sharpness and texture where noise used to exist, not just a smooth and denoised version of the original image. It works best on images that are already high resolution, such as Raw files from the camera or converted to non-raw formats. When using Denoise Max with Raw files, simply add another denoise on top of the Raw Denoise The model is located in the Denoise enhancement control under the AI model selector. Denoise Max can be used instead of Raw Denoise models for Raw files. For high resolution images with high noise, select Denoise Max from the AI model selector to process. Denoise Max runs on Neuroserver which processes locally for NVIDIA, AMD, and Apple Silicon devices, just like Wonder 2 and other Neuroserver based models. For users with other hardware (Intel Mac, Intel GPU) or slow GPU processing, cloud render is available up to a maximum of 100MP in size. If your images have high ISO noise, were shot in low light, or just haven’t responded well to standard denoise models, Denoise Max is the place to start. We want to hear how it performs on your images, especially on shots that have given standard denoise models trouble in the past. Super Focus v3 — Natural Results for Extreme Blur Super Focus has been one of our most used models for recovering blurry images that other tools can’t fix. For cases where standard sharpening falls short, Super Focus is the go-to solution. Super Focus v1 and v2 were impressive for their sharpening capabilities, but the output wasn’t always convincing. Results could look visibly AI generated and unnatural, with smooth textures. Sharpness comes with harsh lines and missing details. Super Focus v3 is a new generative model built to address the shortcomings of it’s predecessors directly. It is capable of creating realistic sharpness and fill in missing details that you expect in a high quality image. Especially with fine details like hair, skin, or natural textures we find that this model significantly outperforms Super Focus v1 and v2. For best results, use Super Focus v3 on images that are blurry or soft and that other sharpening tools have not been able to recover. Because the model is designed not to oversharpen, it is safe to run multiple passes on the same image when a single pass isn’t enough. Each pass recovers additional detail without introducing the harsh edges or halos that would normally be a concern with repeated sharpening. Choose Super Focus v3 from the version dropdown after adding Super Focus to your image. Super Focus v3 runs on Neuroserver which processes locally for NVIDIA, AMD, and Apple Silicon devices, just like Wonder 2 and other Neuroserver based models. For users with other hardware (Intel Mac, Intel GPU) or slow GPU processing, cloud render is available up to a maximum of 100MP in size. We want to hear how it performs on your images, especially on shots that have given previous Super Focus versions or other sharpening tools trouble in the past. Drop your results and feedback in this thread. Known Issues
• Color shift with High Fidelity v3 Changelog
• Add Upscale - High Fidelity v3 model for local render
• Add Wonder 3 model through Neuroserver for NVIDIA, AMD, and Apple Silicon devices
• Add Wonder 3 cloud render
• Add Denoise Max model through Neuroserver for NVIDIA, AMD, and Apple Silicon devices
• Add Denoise Max cloud render
• Add Super Focus v3 model through Neuroserver for NVIDIA, AMD, and Apple Silicon devices
• Add Super Focus v3 cloud render
• Fix image analysis crash when models are incomplete or missing
• Fix face detection crash in image analysis for some images
• Fix image quality detection crash in image analysis
• Fix Wonder 2 error running model in cases where the model file is incomplete or missing

…

Hello everyone! Topaz Photo 1.4.0 is here! This release is focused on making Topaz Photo smarter, leaner, and faster to set up. We’re introducing a new processing mode for Wonder 2, quick install options in the installer for a faster setup, and under-the-hood upgrades that make the app more efficient. Here’s what’s included in the Topaz Photo v1.4.0 - v1.4.1 release:

• Auto Mode for Wonder 2 — Pre-downscaling Wonder Recommendation
• Faster Installation — Recommended & On-Demand Model Download
• Faster Analysis on Mac — Improved image analysis efficiency to reduce analysis time Topaz Photo v1.4.0 Released March 27th, 2026 Installers: Windows : Download (v1.4.1 to fix model download issues in installer and in-app for certain Windows devices) Snapdragon : Download Apple Silicon Mac : Download Intel Mac : Download Auto Mode for Wonder 2 — Fix False Resolution and Low Detail One of the trickier image problems to solve is false resolution, where an image has been upscaled or resampled to a larger pixel size but the actual detail doesn’t match those dimensions. Standard upscaling models tend to produce poor results on these images, and until now Autopilot had no way to detect the issue or point you toward a better option. The same applies to images that are heavily blurred or simply low in recoverable detail. Wonder 2 is great for low and medium resolution images. It does not handle false resolution images with normal scale and size controls. We’ve added a new analysis model to Autopilot Analysis that looks for these conditions. When low detail or false resolution is detected, using Wonder 2 will automatically select its Auto mode. In Auto mode, Wonder 2 determines the appropriate output size based on the actual recoverable detail in the image rather than its nominal pixel dimensions. When Autopilot selects this recommendation, the output size is set automatically with no manual configuration needed. Recommended & On-Demand Model Downloads Installing Topaz Photo has always meant downloading every model upfront, including large specialized models that most people use rarely. This made the installation very slow and storage-heavy before you could even open an image. The reason comes down to model size. The core editing models covering Denoise, Sharpen, Upscale, Face Recovery, Lighting, and Color are compact and cover the vast majority of workflows. The generative models are significantly larger and produce strong results, but they are designed for rarer and more specific image situations. Bundling everything together meant new users were waiting through a long download for models that are less commonly used in their workflow. The installer now allows you to decide which models to download. Recommended models includes all the analysis and core GAN models: everything you need for Denoise, Sharpen, Upscale, Face Recovery, Lighting, and Color. Download is fast and the full standard editing experience is available immediately. All models includes Remove, Super Focus, Dust & Scratch, Wonder, Upscale - Recover v3, and Upscale - Standard MAX. If you choose recommended models and later use a feature that requires a model you don’t have, the application will download it automatically on demand. No need to reinstall or manually manage anything. NOTE: the processing ETA for generative models on the first use will be inaccurate due to the models downloading. If you plan to use the app offline or know you will need the generative models regularly, we recommend selecting all models at install. Faster Autopilot on Mac Autopilot analysis runs on every image you open, which means any improvement to analysis speed has an outsized effect on the experience, particularly for the first file loaded in a session. In looking at where time was being spent, we identified a few models that had become bottlenecks. For each one we looked for improvements, whether that meant finding a smaller model variant that produces the same results or changing how the analysis models are executed. On Mac, the results are significant. Analysis time in testing dropped from 19 seconds in v1.3.3 to under 8 seconds in v1.4.0, more than a 50% reduction. Windows was already running analysis quickly. We made some improvements there as well, though the new false resolution detection model added in this release offset most of the gains, keeping overall analysis time roughly flat. Changelog
• Auto mode for Wonder 2
• Recommended and all model options in installer
• Just in time model downloads
• Faster image analysis on Mac Esther Huynh Product Manager Image AI 99 posts - 42 participants Read full topic

Hello! This release adds AMD GPU support for Wonder 2 local rendering. We’re also introducing SSO for Enterprise, making it easier for teams to login to their applications without managing separate credentials. Plus a fix for bugs due to locale issues on Windows and batch processing errors. Hotfix v1.3.3:

• Fixed login issue
• Fixed errors with RAW Denoise
• Fixed errors with Remove and Spot Healing Below is what’s included in the Topaz Photo v1.3.2 release:
• Wonder 2 Local Render for AMD: AMD GPU users on Windows can now run Wonder 2 entirely on their own device
• SSO for Enterprise: Log in to Topaz Photo using your company’s identity provider. Email enterprise@topazlabs.com for more details. You can find the installer links and the full changelog below for this version of Topaz Photo. For any issues, make sure to send us an email to support@topazlabs.com Topaz Photo v1.3.3 Released March 11th, 2026 Windows: Download Snapdragon: Download Apple Silicon Mac: Download Intel Mac: Download Wonder 2 Local Render for AMD When we launched Wonder 2 local rendering, we rolled it out first for NVIDIA GPUs and Apple Silicon. AMD has been the most-requested addition since, and today it joins the lineup. Local rendering means your images stay on your machine with no upload times, no cloud dependency, and secure local processing. Wonder 2 runs directly using your AMD GPU, with similar output quality to the cloud version. If you’ve been waiting on this one, it’s here. As a reminder, local rendering is now supported on:
• AMD GPUs: 8GB VRAM or more required for dedicated GPU. 24GB RAM or more required for integrated GPU.
• NVIDIA GPUs: 8GB VRAM or more required.
• Apple Silicon: 12GB RAM or more required. A note on your first run: the first time you use Wonder 2 locally, the application will need to unpack the model. This may take a few extra minutes. Subsequent runs will be significantly faster. SSO for Enterprise Enterprise teams can now sign in to Topaz Photo using their company’s existing identity provider. Simply login with SSO and the application will detect then connect to your company login page. For more information, please contact enterprise@topazlabs.com. Changelog
• Add Wonder 2 local processing for AMD graphics cards
• Add Enterprise SSO
• Fix generative models not working on Windows devices with foreign locale
• Fix Raw Denoise having incorrect values on Windows devices with foreign locale
• Fix Upscale occasionally erroring during batch export Lingyu Kong Technical Product Manager Image AI 49 posts - 22 participants Read full topic

We mistakenly released v1.3.0 with Wonder 2 requiring Founder status to use local render. As a result, We are releasing v1.3.1 with Wonder 2 local available to all users, no Founder status required. Changelog

• Wonder 2 local render no longer requires Founder status
• Adjust lighting no longer added automatically by Autopilot Topaz Photo v1.3.1 Released February 27th, 2026 Installers: Windows: Download Snapdragon: Download Apple Silicon Mac: Download Intel Mac: Download Hello everyone Topaz Photo 1.3.0 is here! This release brings a major milestone for Wonder 2, enabling this new model to render locally. We first introduced Wonder 2 as a cloud-only model, but starting today you can run it entirely on your own device for greater privacy and offline workflows. To make this possible, we’re introducing NeuroServer, a new technology we’ve built to enable larger, more powerful models like Wonder 2 to run locally with Topaz Photo. NeuroServer opens the door for us to bring even more capable models to your desktop in the future. This update includes a fix for the Apple Photos save issue, along with several other bug fixes to improve overall stability. For Mac devices, we have updates to minimum requirements and installers. We are increasing the minimum requirement for macOS to 13 (Ventura) and creating separate installers for Intel and Apple Silicon Mac devices. The in-app updater will detect and download the correct installer for your device. Below is what’s included in the Topaz Photo v1.3.0 release:
• Wonder 2 Local Render: Our most advanced realism model, now available to run fully on your device
• NeuroStream & NeuroServer: New local inference technology enabling larger models to run within Topaz Photo
• Offline Authentication for Enterprise: Enables teams to authenticate and work in fully offline environments. Email enterprise@topazlabs.com for more details. You can find the installer links and the full changelog below for this version of Topaz Photo. For any issues, make sure to send us an email to support@topazlabs.com. Topaz Photo v1.3.0 Released February 26th, 2026 Installers: Windows: Download Snapdragon: Download Apple Silicon Mac: Download Intel Mac: Download Wonder 2 Local Render Wonder 2 quickly became a fan favorite after its launch, delivering artifact-free enhancements, reliable text preservation, and our most powerful realistic recovery to date. The catch was that Wonder 2’s resource demands meant it could only run in the cloud. That changes today. With the introduction of NeuroStream and NeuroServer, we’ve built the infrastructure to bring Wonder 2 to your local machine. These technologies allow larger, more demanding models to run directly on your device — and Wonder 2 is the first to take advantage of them. Local rendering is currently supported on the following hardware:
• NVIDIA GPUs: 8GB VRAM or more required
• Apple Silicon: 12GB RAM or more required If you’re on Intel Mac, Windows AMD GPU, or Windows ARM (Snapdragon), Wonder 2 will continue to use cloud render only. For supported hardware, you can choose between local and cloud render depending on your preference. The two models have a slightly different character: the local model renders a bit sharper and less grainy than the cloud version, with particularly strong handling of faces and skin detail. If portraits are a big part of your workflow, it’s worth trying both and seeing which look you prefer. A note on your first run: the first time you use Wonder 2 locally, the application will need to unpack the model. This may take a few extra minutes. Subsequent runs will be significantly faster. With local rendering now available, you can process as many images as you want directly on your device. No upload times, just Wonder 2 running locally. NeuroStream & NeuroServer Behind Wonder 2’s local rendering is a new technology from our research team at Topaz Labs. As our models have grown more powerful, so have their hardware demands. The best results were increasingly locked behind extremely powerful GPUs, limiting how many users could actually take advantage of them locally. As those requirements kept growing, we knew we needed to rethink how we build, deliver, and run these models. That rethinking led to NeuroStream. NeuroStream is a proprietary, industry-first technology that reduces VRAM requirements by up to 95%, allowing large models like Wonder 2 to run on everyday hardware without sacrificing output quality. The only tradeoff is a minor reduction in processing speed. What once required an extremely powerful GPU accessible only on the cloud can now run on the hardware most of our users already have. To use NeuroStream on your device we’ve built NeuroServer. This lightweight local server runs on your machine when you select a model that requires it. Topaz Photo will automatically spin up NeuroServer in the background, load the model, and process your images. When it’s no longer needed, the server shuts down on its own. This opens a new chapter for what’s possible in Topaz Photo. NeuroStream removes the biggest barrier to running powerful models locally, and we’re already working on bringing more models to the application using this technology. We’re excited about what’s ahead as we break down barriers for AI processing. Offline Authentication for Enterprise For enterprise teams that need to work in fully air-gapped or restricted network environments, we’re bringing back offline authentication in Topaz Photo. This allows your team to authenticate and use Topaz Photo without requiring an internet connection, giving IT administrators the control and flexibility they need to deploy Topaz Photo in secure, offline workflows. Offline authentication is available exclusively for Topaz Photo Enterprise users. For more information, please contact enterprise@topazlabs.com. Changelog
• Wonder 2 local render for NVIDIA and Apple Silicon
• Neuroserver deployment for NVIDIA and Apple Silicon
• Separate Intel Mac and Apple Silicon Mac installer
• Increased minimum macOS to 13 for Intel Mac and Apple Silicon Mac
• Add offline authentication for enterprise
• Add support for custom monitor color profiles
• Add tooltip for Remove v2 not supported on macOS 26 with M1 chip
• Add Open Log Folder option to Get Help button in header
• Add Clear CoreMLCache option to Mac > Help menu
• Updated links to docs, forums, and support in Help menu
• Fix Apple Photos plugin save failing due to bad metadata
• Fix face recovery placing faces incorrectly when used after cloud render
• Fix incorrect account administrator shown for pro and enterprise groups
• Fix Upscale and Wonder are disabled tooltip when used through Photoshop > Filter plugin
• Fix CoreMLCache error unpacking model file taking up excessive storage Lingyu Kong Technical Product Manager Image AI 188 posts - 44 participants Read full topic

Hello! Today we have a patch release with local processing on Mac with the Remove v2 and Recover v3 models, plus fixes for reported issues from the last release. Remove v2 and Recover v3 do not work on M1 devices with macOS 26 (Tahoe). We are working with Apple to fix this issue. You can find the installer links and the full changelog below for this version of Topaz Photo. For any issues, make sure to send us an email to support@topazlabs.com We are working on more fixes and feature updates, stay tuned! Topaz Photo v1.2.1 Released February 6, 2026 Windows: Download Mac: Download Snapdragon: Download Changelog

• Recover v3 local processing for Mac (except on M1 w/ macOS 26)
• Remove v2 for macOS 26 (except on M1)
• Removed credits from account dropdown due to unlimited cloud render
• Fixed Sharpen opacity slider not longer appearing
• Fixed text field issue with scale and adjust lighting with foreign locales on Win
• Fixed HEIC images failing to export
• Fixed face selection resetting to all when switching from current image to previous image with face selection Lingyu Kong Technical Product Manager Image AI 71 posts - 20 participants Read full topic

Hello everyone Topaz Photo 1.2.0 is here! This release is a major step forward in realism, reliability, and professional-quality output. We’re introducing multiple new and upgraded models designed to handle challenging images, recover fine detail, and deliver cleaner, more natural results across your entire workflow. We’re especially excited to launch Wonder 2, our most advanced realism model to date built with artifact prevention and text preservation as core priorities, making it a powerful new option for professional and commercial use. Below is what’s included in the Topaz Photo v1.2.0 release:

• Wonder 2 — One-Click Realistic Enhancement for Challenging Images
• Recover v3 — Our Best Diffusion Upscaling
• Remove v2 — Cleaner Results With Better Scene Awareness
• Grain — The Finishing Touch for Natural Results When deciding between the Wonder and Recover models:
• Use Wonder 2 when realism and professional polish are the top priority
• Use Recover 3 when you need local processing or want more creative control over texture Topaz Photo v1.2.0 Released January 22th, 2026 Installers: Windows: Download Mac: Download Snapdragon: Download Wonder 2 - One-Click Realistic Enhancement for Challenging Images This is our most impressive all-in-one realism model so far. It’s built to handle extremely difficult images and produce outputs that look clean, natural, and professional. Wonder 2 is a great choice when realism is the top priority and you want a safe model for professional work. Wonder 2 is has significantly reduced artifacting delivering our cleanest, most reliable results to date. It avoids haloing, texture smearing, edge distortion, and unnatural sharpening. This helps produce outputs that look more natural, professional, and ready to use. It also is text-safe, helping keep logos, signage, and readable text intact when source quality allows. This makes Wonder 2 a strong choice for business, marketing, and commercial images where clarity and accuracy are important. Images with very challenging text have met their match. Before and after processing with Wonder 2. And an impressive close-up of the output. Wonder 2 is intentionally simple to use. There are no creativity sliders or tuning parameters. Select the enhancement, choose your upscale size if needed (you can also run 1x to improve your image without resizing) and run it. The model handles the complexity behind the scenes, making it ideal when you want consistent, high-quality output without manual adjustment. Wonder 2 performs best on low-resolution or challenging source images that need strong cleanup and enhancement. For already high-quality images, it may be unnecessary, but it can still be useful for light cleanup or consistency improvements. Because of the high requirements to run this model, Wonder 2 is currently available as a cloud-only feature. The maximum cloud output size is 128MP. Recover v3 - Our Best Diffusion Upscaling Recover v3 represents our highest quality approach to AI upscaling. It’s built to produce photographic texture, not artificial sharpening or overly processed results. Instead of simply increasing resolution, Recover v3 focuses on reconstructing fine surface detail for things like fur, skin texture, foliage patterns, and fabric structure. This makes it especially strong for nature photography, wildlife, and portraits, where realism matters most. To control the output we introduced a Creativity setting which lets you decide how much texture the model will add. The Low setting is conservative and close to the original image, Medium is our recommended setting for details and natural sharpness, while High produce more fine detail for a sharper output. This flexibility gives you control depending on the source quality and the look you’re trying to achieve. Keep in mind that higher creativity levels can introduce background artifacts, so it’s best used when powerful recovery is required. Recover v3 supports any upscale size, works with batch processing, and can run both locally and in the cloud. For most users, cloud rendering is recommended for speed. The maximum cloud output size is 128MP. Local processing is ideal when privacy, offline workflows, or unattended batch jobs are more important than raw performance. Recover 3 is slower than Recover v2 (for Gigapixel users who have tried it previously) in exchange for higher quality. Recover v3 works best on lower-quality images that still contain usable detail. If your source is already high resolution and clean, this model is often unnecessary. It also isn’t ideal for images dominated by text or logos, which diffusion models still struggle to reproduce accurately. Note: Recover 3 is not supported on Windows ARM devices due to hardware constraints. Local processing on Mac disabled, we will continue to work on this. Remove v2 - Faster Cleanup With Cleaner Results Remove has received a major upgrade in version 2, delivering faster performance, improved scene understanding, and more natural-looking fills. Remove v2 now fully replaces Remove v1 as the new default removal experience. The new model is 100% faster than Remove v1, making it easier to iterate on edits and perform everyday cleanup without slowing down your workflow. It’s also better at handling complex removals where Remove v1 failed, including objects in the foreground, people, and detailed backgrounds with overlapping textures. Remove v2 analyzes surrounding structure and texture more intelligently, resulting in more believable replacements and fewer visible seams or visual artifacts. For the highest quality results, we still recommend using smaller, more precise masks whenever possible. While Remove v2 is more capable with large selections, tighter masks allow the model to better match nearby detail and produce cleaner fills. Remove v2 runs locally on both Windows and Mac, delivering fast, responsive performance for everyday editing workflows. Windows ARM devices and macOS 26 (Tahoe) are not currently supported for this model. Grain - The Finishing Touch for Natural Results Grain is a new enhancement designed to solve a common problem with AI image processing: overly smooth, artificial-looking textures. After denoise, sharpen, upscaling, or face recovery, images can sometimes lose natural textures or depth. Grain helps bring that back by adding controlled, realistic texture across the entire image. This tool is meant to be used as a finishing step, the last enhancement in your processing, to subtly restore organic texture, improve atmosphere, and make results feel more photographic and less “AI-generated”. Avoid using this before other AI models as the grain will be distorted or processed away. Grain includes three generation modes, with an example for each:

Gaussian - Adds fine, randomized grain that includes subtle color noise across channels. Best for recreating natural sensor noise and modern digital texture with smooth, even distribution.

Grey - Applies consistent monochromatic grain without introducing color noise. Ideal when you want added texture and depth while keeping color clean and stable.

Silver Rich - Simulates classic analog film grain with organic clumping and higher contrast variation. Designed for cinematic and vintage looks where texture becomes part of the aesthetic. Each mode gives you different stylistic textures to match your image. You also get full control over grain strength, intensity, and size, allowing you to dial in effects from subtle realism to more stylized film looks. The effect is applied directly to your export and processes nearly instantly, so it won’t slow down your workflow. Known Issues

• Cloud render progress not updating for Wonder 2 and Recover 3 cloud render
• Disabled Recover v3 Mac local processing, cloud only for now
• Disabled Remove v2 macOS 26 (Tahoe) local processing Changelog
• Add Wonder 2 cloud render
• Add Recover v3 cloud render, Win local render
• Add Remove v2
• Add Grain Lingyu Kong Technical Product Manager Image AI 107 posts - 33 participants Read full topic

Hello! We are releasing the v1.1.1 patch, fixing Sharpen - Portrait set as the default model for Sharpen. Please update to the latest version for this fix. Changelog

• Fixed Sharpen - Portrait model set as the default for all Sharpening instead of using Auto model selection v1.1.1 Released December 22th, 2025 Windows: Download Mac: Download Snapdragon : Download Hello everyone! We’re happy to introduce Topaz Photo v1.1.0, the latest version of the app. As part of our continued push toward more realistic, natural-looking results, this release introduces three new and improved models designed to better handle real-world images. In v1.1.0, you’ll find:
• Portrait Sharpen — High Resolution Detail for Faces and People
• Adjust Lighting v3 — Better Results in Difficult Lighting
• Dust & Scratch v2 — Cleaner Restorations We also released Wildlife Sharpen in the previous version, which is still very much worth trying if you work with animal or wildlife images. Together, these updates continue our focus on delivering cleaner, more lifelike results across a wide range of photo types. Alongside these model updates, we’re continuing to expand RAW camera support. This release adds support for 13 new cameras, helping ensure your RAW files import and process correctly from the start. We’ll keep adding support for new cameras as they become available so you can rely on Topaz Photo in your existing workflow. v1.1.0 Released December 18th, 2025 Windows: Download Mac: Download Snapdragon : Download Portrait Sharpen — High Resolution Detail for Faces and People We’re introducing Portrait Sharpen, a new model trained specifically for portraits and people photography. Portraits make up a large percentage of the images processed in Topaz Photo, yet none of the previous Sharpen models were designed for this image type. Existing models often produce results that look smooth, artificial, or simply did not have noticeable improvement especially on medium and high-resolution photos. The Portrait Sharpen model was trained on high-quality portrait images to better handle the fine details that make people look natural — hair texture, facial features, and clothing details. The goal is to deliver sharp, clean detail without exaggeration or the “plastic” effect that can appear with older models. To use it, add Sharpen then pick it from the model selector. For the Best Results This model should be used only on high-resolution (5MP or larger) portrait images that are already denoised and deblurred. RAW images are the best to use with Portrait Sharpen. We recommend running Denoise and Sharpen first to fix noise and blur. Portrait Sharpen will run best as a finishing step, as it will not perform as well on images beyond a certain blur level. Attached are sample files you can test the new model with. For smaller or low-resolution portraits, use Upscale first to increase pixel detail, then apply Portrait Sharpen as a final step for natural, lifelike results. Click here to download sample images for Portrait Sharpen. Here is an example of an eye sharpened with the Standard model (original on left, output on right). The eyebrow hairs are smudged together, skin details are over-sharpened and changed. Patterns and textures are created on the skin. And an example with the Portrait model. Skin texture is enhanced instead of over-sharpened. Details are amplified to become eye-caching (excuse the pun). For this face, the Standard model enhances the face but does not enhance the skin texture or facial hair. There is also a noticeable shift in brightness on the facial hair. With the Portrait model, the image is enhanced without a change in exposure. Skin details are finer and more natural. Facial hair is sharpened without losing the quality of hair. Please try it on a range of portrait images — close-ups, group photos, and candid shots — and let us know what you think. Do faces, hair, and fabrics look more realistic? Does it produce the level of natural detail you expect? Adjust Lighting v3 — Better Results in Difficult Lighting We’re introducing Adjust Lighting v3, an update to one of the most widely used models in Topaz Photo. Adjust Lighting has always been designed to optimize lighting. The v2 model is able to fine-tune already well-lit photos and fix mild lighting issues. However, v2 struggles with underexposed or overexposed images. With v3, we focused on expanding the model’s ability to correct challenging lighting conditions. The new model is trained to better recover detail from dark shadows and blown highlights, making it more effective across a wider range of real-world images. In addition to improved lighting correction, v3 produces results that are slightly more vibrant and visually pleasing compared to v2, while still maintaining a natural look. If you want to push vibrance even further, toggle on the color correction to further enhance colors in your image. Below, we’ll share example before-and-after results demonstrating how Adjust Lighting v3 performs on underexposed, overexposed, and mixed-lighting images. Click here to download sample images to use with the new model. Please let us know what you think about the results. Does the model strength feel right? Do the lighting results look natural, or realistically enhanced? Any feedback will help us tune the model output to deliver better image quality to you. Dust & Scratch v2 — Cleaner Restorations Dust & Scratch is a powerful, time-saving tool for anyone working with film scans, archival photos, and damaged prints. With Dust & Scratch v2, we’re introducing a major model update focused on improving cleanup quality while better preserving original image detail. This new model includes several key improvements:
• Better dust removal for small particles and fine surface debris
• Better scratch removal for thin scratches
• Improved edge handling, eliminating cases where borders and edges had worse results than the rest of the image A major piece of feedback we have heard so far is that the v2 model can remove details from the image. We will continue to improve the model to improve fidelity and detail preservation now that it is able to clean dust & scratches with high confidence. Dust & Scratch v2 is available for both local render and cloud render so you can use it on-device or take advantage of faster processing in the cloud. Changes to Workflow The v1 model is no longer available for use. All local and cloud render will use the v2 model only as the v2 results are much better the previous model. We removed the spot healing step that ran directly after Dust & Scratch processes, as this tool is now included in the enhancement list to be used as needed. Of course, we have to show off the new model with some examples. Click here to download images for testing. Before and afters with Dust & Scratch v2: We hope that Dust & Scratch v2 will be an important part of your image restoration workflows to save you time. Let us know if it’s working for your needs, especially if we can improve it further. New Camera Support Added We’ve added RAW support for 13 additional cameras in this beta, continuing our effort to ensure your files import and process correctly from the start. If you shoot with any of the cameras below, you should now be able to open and work with your images in Topaz Photo without extra conversion steps:
• OM-3
• Panasonic ZS200D
• Nikon Z5 II
• Panasonic Lumix S1 RII
• Fujifilm X-T50
• Hasselblad X2D II 100C
• Hasselblad CFV-100C
• Fujifilm GFX100RF
• Fujifilm X-E5
• Panasonic DC-ZS99
• Sony RXR1 III
• Canon PowerShot V1
• Nikon Coolpix P1100 Please try loading RAW files from these cameras and let us know if you run into any issues with import, color, or processing. Your feedback will helps us validate and finalize camera support for these. Known Issues
• HEIC import is broken. We will be fixing this in the next patch. Changelog
• Sharpen - Portrait model
• Adjust Lighting v3 model
• Dust & scratch v2 model
• Fixed TIF thumbnails displaying incorrectly in filmstrip
• Fixed Wonder cloud render failing with some upscale values
• Fixed Apple Photo plugin export failing if the image was stored on an external drive
• Updated Adjust lighting to use All selection instead of Auto by default
• Updated Super Focus to use Auto selection by default
• Added RAW file support for 14 cameras Lingyu Kong Technical Product Manager Image AI 141 posts - 41 participants Read full topic

Hello! I’m pleased to announce the latest update for Topaz Photo with the Sharpen - Wildlife model, Intel Mac support, and fixes for major issues since the application release. You can find the installer links and the full changelog below for this version of Topaz Photo. For any issues, make sure to send us an email to support@topazlabs.com We are working on more fixes and feature updates, stay tuned! Topaz Photo v1.0.2 Released November 17th, 2025 Windows: Download Mac: Download Snapdragon: Download Wildlife Sharpen — Natural Detail for Wildlife Images We’re introducing Wildlife Sharpen, a new model designed specifically for fine, natural detail in wildlife photography. When researching places to improve Topaz Photo, better sharpening for wildlife comes up frequently in fur, feathers, whiskers, scales, and delicate textures. Existing sharpen models in Topaz Photo are for general sharpening which smooths away these details, producing an artificial, plastic result. The Wildlife model aims to preserve lifelike textures while keeping larger structures crisp without that over-sharpened halo look. Below are before and after examples. Low resolution JPG image, upscaled first, then sharpened. The GIF only shows the sharpening step. Noisy raw image, denoised and sharpened. Here are sample images to download and try processing. Best practices for using the Wildlife model:

• Use on high-resolution images (5MP or higher) with low–medium blur to keep lifelike fur/feather detail and avoid “plastic” looks.
• Not for heavy blur recovery, the other sharpen models will be better for cases where the subject is significantly out of focus or smeared by motion.
• Treat as a finishing step once the image is in good shape, after denoise or other adjustments.
• For low-resolution files, Upscale first to increase resolution and generate enough pixels for the model, then apply the Sharpen - Wildlife model reveal convincing micro-detail. Intel Mac Support We’re re-enabling Intel Mac support in Topaz Photo. Previously, Intel-based Macs were blocked from installation because we expected newer versions of the app would no longer be compatible. However, we’ve confirmed that Intel Macs can still process normally with all non-generative models on device and take advantage of unlimited cloud render for generative models that cannot run locally due to hardware requirements.
• Intel Mac users can now install and run Topaz Photo again.
• The installer will skip generative model downloads
• Generative models will run in the cloud only
• All other enhancement models (Sharpen, Denoise, Recover Faces, etc.) work as before, fully on-device. With unlimited cloud rendering now available, Intel Macs can also run generative models through the cloud at no cost. Local rendering for generative models will be disabled as these models are not compatible with Intel Mac hardware. The installer will skip downloads for generative models to save storage space and decrease installation time! This change lets Intel Mac users get access to new features and updates without interruption. If you’ve been waiting to upgrade or reinstall, you can now do so with confidence as Topaz Photo is fully supported on your Intel Mac once again. Batch Render Generative Models in Cloud You can now batch-process generative models in the cloud using Topaz Photo. With Unlimited Cloud Render available, this update lets you send multiple images at once to be processed on our servers. This should make it easier, faster, and more reliable to run the heavier, more powerful models in your workflow. Batch cloud render is possible with:
• Standard Max
• Wonder
• Dust & Scratch
• Super Focus v2 To use it:
• Import a batch of images
• Select an image in the batch
• Use one of the above models with cloud render on an image
• Select all images in your batch with Ctrl/CMD + A to apply the generative model with cloud render to other images
• Export the batch Every image that inherits those settings will automatically be processed in the cloud as soon as the workflow reaches a generative model. This is a great option for anyone who wants the speed and consistency of cloud processing, especially for the models that require more compute power. It’s also a major boost for Intel Mac users who can now run all generative models through the cloud even though their hardware doesn’t support them locally. Give batch cloud rendering a try and let us know how it improves your workflow! Changelog
• Add Sharpen - Wildlife model
• Add Intel Mac support
• Batch cloud render enabled for: Standard Max, Wonder, Dust & Scratch, Super Focus v2
• Update Upscale + Recover Faces logic to produce highest quality face output
• Fix Photoshop Filter plugin export failing if dimensions were changed
• Cloud processing should be able to apply current settings and process on cloud now
• Add modal with solution to error loading model when used as plugin
• Fix Photoshop Automate plugin having incorrect name
• Fix filmstrip tooltip showing incorrect model when using Super Focus v1 cloud render Lingyu Kong Technical Product Manager Image AI 163 posts - 36 participants Read full topic

Hello! Today we have a patch release with fixes for the most frequent issues since release. You can find the installer links and the full changelog below for this version of Topaz Photo. For any issues, make sure to send us an email to support@topazlabs.com We are working on more fixes and feature updates, stay tuned! Topaz Photo v1.0.1 Released September 23th, 2025 Windows: Download Mac: Download Snapdragon: Download Changelog

• Fix for seat management blocking login
• Fix pricing modal links adding wrong products to cart
• Dynamic Topaz Photo feature modal size and updated close button color
• Fix showing original image when any processing happens after Wonder is added
• Fix upscale resolution (ppi) field not showing up
• Fix Photoshop plugin error when Photo AI is also installed
• Fix enhancement reverting to default state when adding another enhancement and coming back
• Fix Wonder and Recover Faces pasting faces in wrong location Lingyu Kong Technical Product Manager Image AI 183 posts - 40 participants Read full topic

Hello! Topaz Photo Official Release Today we’re thrilled to announce a brand-new Topaz Photo release that brings some of our most exciting features to date. We know many of you are adjusting to the new subscription model, and our goal with this update is to make Topaz Photo more valuable and accessible than ever. Here is the first release of Topaz Photo with a impressive set of new AI models and new features:

• New Standard MAX Upscaling model - local and cloud render
• New Wonder model - local and cloud render
• Unlimited + free cloud render
• Healing brush as a standalone enhancement
• Opacity control for Sharpen and Super Focus
• Accordion style controls for all enhancements
• Upscale anywhere in the enhancement stack
• Updated header and footer
• New selection workspace with updated selector for brush type
• Flatten layers function to replace locking edits
• Windows ARM (Snapdragon) support
• Lightroom Cloud plugin support We will no longer sell perpetual licensed products moving forward, but we will continue to update them to maintain compatibility with major OS updates for as long as possible. Here are the installers, a quick FAQ to address any confusions you may have, followed by the longest release thread I have seen on these forums. Topaz Photo v1.0.0 Released September 17th, 2025 Installers: Windows: Download Mac: Download Snapdragon: Download What is Topaz Studio? Topaz Studio is our collection of desktop apps (Topaz Video, Topaz Gigapixel, Topaz Photo) as well as our web applications (Bloom, Astra, Express), mobile iOS app, and more! In short - it’s everything that Topaz has to offer to enhance your images and videos. How does Topaz Photo fit into Studio? Topaz Photo is available as a part of our new Studio Launch. With this launch, Topaz Photo will only be available under a subscription license. Topaz Photo will install into a new directory so you can try it out, and of course you’ll still have access to Photo AI forever under the legacy perpetual license. Note that new features and new AI models will be coming only to Topaz Photo, along with the other products in the Studio suite. What if I already own Photo AI or other Topaz products? Purchased a Topaz product within the last year? Then you get to try Studio for free for the length of your remaining license. You’ll also get some extra benefits. If you are a Topaz customer with an active license and you maintain your new studio subscription, you’ll be considered a Topaz Founding Customer which will give you access to some of our more powerful Pro models such as Starlight and other Pro features at no extra cost as well with your Individual license of Topaz video. Can I buy the individual products or a perpetual license? Topaz Studio is an incredible value - all for one low monthly price. You can still purchase subscriptions to the individual products as you wish, but you’ll get the best value with the Studio or Desktop collection bundles. We will no longer sell perpetual licensed products moving forward, but we will continue to update them to maintain compatibility with major OS updates for as long as possible. When will I get my free studio upgrade and access? Please note that the transition plan is underway and may take a few days - but if you’ve already purchased and hold an active license for Photo AI, or if you own more than 2 Topaz Products on an active license, you’ll have automatic access to Topaz Photo at no extra cost once the transition is complete. We’ll keep you updated via email, and you can check the status of your account on the My Account page. If you have questions about the transition to Studio, please visit this forum thread: Topaz Studio New Standard MAX Upscaling model The Standard MAX model is a powerful new upscaling tool in Topaz Photo. This model is built on new architecture, producing very high-quality outputs similar to generative upscaling models in Gigapixel AI while significantly lowering the hardware requirements and high processing time. Standard MAX can run on a wide range of devices — making advanced restoration more accessible than ever. Standard MAX delivers outstanding results across all types of input images, but it truly shines on low-resolution photos where it generates incredible photorealistic detail that surpasses anything currently available in Topaz Photo. The results are clean and natural, with refined textures that are hard to achieve in other AI upscaling models. While we highly recommend trying it on low-res images for truly jaw-dropping outputs, Standard Max also performs exceptionally well on medium and high-quality images, making it a versatile and powerful choice for a wide range of upscaling needs. Before and after on a low resolution image Try it for yourself! Here are test images you can use with Standard Max, including the examples above. To use Standard Max, add Upscale to your image and pick it from the AI model grid select. Select a scale and whether you want to process locally or on the cloud. After processing completes, adjust Opacity to dial in the exact look you want—from subtle improvements to full recovery. Cloud render is also available for this model, allowing anyone to run it no matter your hardware. NOTE: cloud render for Standard MAX has a 256 megapixel output limit. Wonder Model for Local and Cloud Processing We’re introducing Wonder, a new enhancement designed for professionals who want a simple, reliable way to improve image quality without stacking multiple tools. Traditional workflows can over-process or introduce artifacts when several enhancements are combined. Wonder is an automatic image repair tool to deliver very high-quality, artifact-free results—especially on medium and low-quality images. NOTE: Local rendering for the Wonder model is available for Pro and Founder users. Consumer licenses can only use cloud rendering. Before and after with a low resolution image. It’s able to generate clean outputs, especially with fine details that other models may struggle with. To use the Wonder model, open the enhancements menu and select the new Wonder enhancement. Wonder is able to scale your image up or down. For larger files, use the cloud option to speed up processing. This model is best for images that are soft, noisy, compressed, or low-resolution where you want clean, realistic detail without artifacts. Try Wonder on a variety of medium and low-quality images and tell us what you think. Your input will help us tune defaults and scaling behavior before full release. Unlimited! and Free! Cloud Renders Cloud processing is now Unlimited and Free. That means any image you process through the cloud will cost 0 credits, no matter how many files you process. Run our most powerful models in the cloud with one click for faster results, and importantly without worrying about costs. Note: there is still a maximum output limitation, but any image below that size will process for free. This feature will be available for the following models:
• Super Focus
• Dust & Scratch
• Standard MAX
• Wonder We hope that removing the barriers for cloud render increase your usage for this feature, and significantly improve the processing experience for the new models we have released. For users with less capable graphics cards, this should make the generative models accessible and fast as you can offload your processing to the cloud. Let us know what you think about this feature, especially how we can improve it in the application to make it more useful. Spot Healing now available as a standalone enhancement The Spot healing brush is now available in the enhancements menu. If you’ve used the Dust & scratch model, then you already recognize this tool as it was included as the second step to help remove larger damage that the AI model did not clean up. By turning it into a stand alone tool, we are giving you a fast, lightweight way to clean up small sections of your image without needing to run the full Dust & Scratch workflow. This tool is ideal for removing minor artifacts, blemishes, or imperfections with precision. Just use the brush to select a small area, and as soon as you release, processing begins instantly — no need to adjust settings or switch tools. It’s a quicker and more targeted alternative to the Remove tool, designed to keep your workflow smooth and responsive. Try it out on photos with minor flaws or cleanup needs, and let us know how it feels to use. We’d love to hear your feedback on the results and whether it helps improve your editing process. Opacity control for Sharpen and Super Focus We’re introducing a new opacity control for the Sharpen and Super Focus enhancements, giving you more flexibility to fine-tune the final look of your image. While our sharpening models are powerful, some users have noted that the results can sometimes look unnatural or plasticky—especially on portraits or finely textured areas. New sharpen controls including the new opacity parameter: New super focus controls including the new opacity parameter: Previously, adjusting the strength slider was the only way to control intensity, but it didn’t always offer enough subtlety. With the new opacity slider, you can now blend the sharpened output with the original image, making it easier to strike the right balance between clarity and realism. Upscaled with Super Focus @ 100% opacity - a little over-sharp: Reduced to 50% opacity - much better Accordion-Style Controls We’re excited to introduce a much-requested update: accordion-style controls for enhancements in the right-hand panel. This change is designed to show more of the image preview area while still having quick access to our powerful AI tools. With this new layout, enhancements listed on the right panel are expanded on click to show all your controls. This keeps the interface cleaner and your attention where it matters most—on the image. This update also aligns with our goal of reducing clutter in the workspace, giving you better visibility of your image and simplifying the process of fine-tuning adjustments. Let us know what you think about the updated design! Upscale Anywhere in the Enhancement Stack One of our most requested features is finally here—you can now add Upscale anywhere in the processing stack. Previously, Upscale was locked to the end of the workflow, which limited your ability to improve low-resolution images that needed enhancement before upscaling. With this update, you can now place Upscale before or after tools like Denoise, Sharpen, or Super Focus**, giving you more control over how and when detail is introduced into your image. This helps preserve and amplify fine details before using other enhancements to refine them further. We recommend applying Upscale to increase resolution early, especially on low and medium resolution images where other enhancements may over-process the image or remove too much detail so that Upscale was no longer as effective for improving quality. On the top is an image processed with Sharpen, then Upscale. The bottom image is processed with Upscale, then Sharpen. Same exact enhancements, models, and settings. However the top image looks over-processed and the bottom image looks more natural especially in fine details. Try out Upscale Anywhere and let us know how it works with your images. We’re eager to hear how it impacts your results and helps streamline your enhancement process. Updated Header and Footer – cleaner layout, smarter controls

…