# Diffusers v0.40.0 — Diffusers 0.40.0: New pipelines, tensor-parallel support, improved CLI, and more

- Product: Diffusers (https://whatsnew.fyi/product/diffusers)
- Vendor: Hugging Face
- Date: 2026-08-20
- Version: v0.40.0
- Original notes: https://github.com/huggingface/diffusers/releases/tag/v0.40.0
- Permalink: https://whatsnew.fyi/product/diffusers/releases/v0.40.0

What's New is an index, not a publisher: every entry below links to the vendor's own release notes, which are the authoritative source. Entries are labelled where they are hand-curated sample data, pre-releases, or drawn from a secondary source such as a developer blog.

Reuse: the summaries, labels and curation here are © What's New. Quote freely with attribution and a link back; wholesale republication of the corpus is not permitted — terms: https://whatsnew.fyi/terms. The vendors' own release notes remain their publishers'.

---

- **added** — Add MiniMax-H3 pipeline for generating video and soundtrack together with a single transformer
- **added** — Add MiniMax Music 3 pipeline for producing complete songs up to five minutes long from lyrics and music description
- **added** — Add Stable Audio 3 text-to-audio model generating high-quality stereo audio at 44.1 kHz with three pipeline variants
- **added** — Add LTX2VideoDiffusionDecoderModel and LTX2VideoDiffusionDecodePipeline for a second video decoder over the same latent space
- **added** — Add duration_head to LTX-2.5 for auto-predicting num_frames from text-connector output
- **added** — Add prompt enhancement to LTX-2.5 through separate google/gemma-4-E2B-it checkpoint with enable_prompt_enhancement parameter
- **added** — Add LTX25AutoBlocks for Modular Diffusers
- **added** — Add Wan-Animate-2 pipeline for animating reference character image with motion of a driving video
- **added** — Add JoyAI-Image-Edit-Plus pipeline for multi-image instruction-guided editing accepting 1-5 reference images plus text instruction
- **added** — Add Cosmos 3 Modular pipeline with Transfer support for precomputed control videos
- **added** — Add Cosmos 3 Edge support
- **changed** — Graduate Modular Diffusers out of experimental phase to stable support
- **added** — Add minimal support for tensor-parallel

> [!TIP]
> This release features several new pipelines, including LTX2.5, MiniMax H3, and Wan Animate 2. We're also graduating Modular Diffusers out of the experimental phase and announcing its stable support. Additionally, this release includes minimal support for tensor-parallel. There's a lot more that went down in this release. So, please consult the notes for details. 

##### New Pipelines

###### MiniMax-H3

[**MiniMax-H3**](https://huggingface.co/docs/diffusers/main/api/pipelines/minimax_h3) generates video and its soundtrack together. A single transformer denoises one packed sequence containing the text conditioning, the conditioning media, and the target video *and* audio latents — there is no separate vocoder and no post-hoc audio pass. Its conditioner is a `Qwen3VLForConditionalGeneration` whose unnormalized 50th-decoder-layer hidden state is read instead of the last one.

MiniMax-H3 is integrated as [Modular Diffusers](https://huggingface.co/docs/diffusers/main/modular_diffusers/overview) blocks only — `MiniMaxH3Blocks` and their `MiniMaxH3ModularPipeline` are the whole integration. The conversion ships both checkpoint partitions in one repository and exposes three workflows (`t2va`, `fl2va`, `ref2va`) that can be pruned at `from_pretrained` time so only that task's components are declared and downloaded.

###### MiniMax Music 3

[**MiniMax Music 3**](https://huggingface.co/docs/diffusers/main/api/pipelines/minimax_music3) produces complete songs up to five minutes long from lyrics and a music description, with expressive vocals and long-range structure. It is a hybrid of an autoregressive and a diffusion stage: an 8B Qwen3-based global language model predicts one semantic audio token per frame while a small depth decoder fills in seven residual RVQ codebooks, and their fused hidden states condition a 2.4B flow-matching transformer that produces Flow-VAE latents in overlapping chunks. A DAC-style decoder turns the latents into 44.1 kHz stereo audio.

###### Stable Audio 3

[**Stable Audio 3**](https://huggingface.co/docs/diffusers/main/api/pipelines/stable_audio_3) is a text-to-audio model from Stability AI that generates high-quality stereo audio at 44.1 kHz. It uses a rectified-flow DiT conditioned on a frozen T5Gemma text encoder (via cross-attention) and on duration (a float embedded by `StableAudio3DurationEmbedder` and used for adaptive layer norm), and decodes with the SAME (Semantically-Aligned Music Encoder) autoencoder, `AutoencoderSAME`.

Three pipelines ship: `StableAudio3Pipeline`, `StableAudio3AudioToAudioPipeline`, and `StableAudio3InpaintPipeline`.

Thanks to @buffett0323 for the contribution (https://github.com/huggingface/diffusers/pull/14119).

###### LTX-2.5

[**LTX-2.5**](https://huggingface.co/docs/diffusers/main/api/pipelines/ltx2#ltx-25) reuses the existing `LTX2Pipeline` / `LTX2VideoTransformer3DModel` / `AutoencoderKLLTX2Video` classes — there is no separate pipeline class. The user-visible difference is the text encoder: LTX-2.5 is paired with a Gemma 4 (`gemma4_unified`) checkpoint, loaded automatically from a converted LTX-2.5 repo.

[`Lightricks/LTX-2.5-Diffusers`](https://huggingface.co/Lightricks/LTX-2.5-Diffusers) ships both the distilled DiT (`transformer/`) and the full/SFT DiT (`transformer_full/`), plus everything two-stage generation needs. Alongside the checkpoint support, this release adds:

- `LTX2VideoDiffusionDecoderModel` and `LTX2VideoDiffusionDecodePipeline` — a second video decoder over the same latent space, so latents are interchangeable between decoders.
- A `duration_head` that predicts shot length from the text-connector output, so `num_frames` is auto-predicted by default when the loaded pipeline has one.
- Prompt enhancement through a separate off-the-shelf `google/gemma-4-E2B-it` checkpoint (`enable_prompt_enhancement=True`).
- `LTX25AutoBlocks` for Modular Diffusers ([#14453](https://github.com/huggingface/diffusers/pull/14453))

_[Truncated at 4000 characters — full notes: https://github.com/huggingface/diffusers/releases/tag/v0.40.0]_