From 7e5e9eb8bbd4c85868eafab40b83fd08d3c3a3fa Mon Sep 17 00:00:00 2001 From: Vladimir Mandic Date: Thu, 7 Aug 2025 14:08:29 -0400 Subject: [PATCH] add basic vace support Signed-off-by: Vladimir Mandic --- CHANGELOG.md | 9 ++++++--- TODO.md | 1 - modules/video_models/models_def.py | 12 ++++++++++++ 3 files changed, 18 insertions(+), 4 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 5c535695b..1509dbfb1 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -8,7 +8,7 @@ ### Highlights for 2025-08-07 -Several new models: [Qwen-Image](https://qwenlm.github.io/blog/qwen-image/), [FLUX.1-Krea-Dev](https://www.krea.ai/blog/flux-krea-open-source-release), [Chroma](https://huggingface.co/lodestones/Chroma), [SkyReels-V2](https://huggingface.co/Skywork/SkyReels-V2-DF-14B-720P-Diffusers) +Several new and updated models: [Qwen-Image](https://qwenlm.github.io/blog/qwen-image/), [FLUX.1-Krea-Dev](https://www.krea.ai/blog/flux-krea-open-source-release), [Chroma](https://huggingface.co/lodestones/Chroma), [SkyReels-V2](https://huggingface.co/Skywork/SkyReels-V2-DF-14B-720P-Diffusers), [Wan-VACE](https://huggingface.co/Wan-AI/Wan2.1-VACE-14B-diffusers) Plus continuing with major **UI** work, there is new embedded **Docs/Wiki** search, redesigned real-time **hints**, built-in **GPU monitor**, **CivitAI** integration and more! On the compute side, new profiles for high-vram GPUs and offloading improvements And (*as always*) many bugfixes and improvements to existing features! @@ -34,8 +34,11 @@ And (*as always*) many bugfixes and improvements to existing features! - [SkyReels-V2](https://huggingface.co/Skywork/SkyReels-V2-DF-14B-720P-Diffusers) SkyReels-V2 is a genarative video model based on Wan-2.1 but with heavily modified execution to allow for infinite-length video generation supported variants are: - - diffusion-forcing: T2I DF 1.3B for 540p videos, T2I DF 14B for 720p videos, I2I DF 14B for 720p videos - - standard: T2I 14B for 720p videos and I2I 14B for 720p videos + - diffusion-forcing: *T2I DF 1.3B* for 540p videos, *T2I DF 14B* for 720p videos, *I2I DF 14B* for 720p videos + - standard: *T2I 14B* for 720p videos and *I2I 14B* for 720p videos + - [Wan-VACE](https://huggingface.co/Wan-AI/Wan2.1-VACE-14B-diffusers) + basic support for *Wan 2.1 VACE 1.3B* and *14B* variants + optimized support with granular guidance control will follow soon **Torch** - Set default for ROCm and OpenVINO to `torch==2.8.0` - **UI** diff --git a/TODO.md b/TODO.md index b3b35f3e0..4a8f601f2 100644 --- a/TODO.md +++ b/TODO.md @@ -15,7 +15,6 @@ Main ToDo list can be found at [GitHub projects](https://github.com/users/vladma - Video: LTX PromptEnhance - Video: LTX Conditioning preprocess - [WanAI-2.1 VACE](https://huggingface.co/Wan-AI/Wan2.1-VACE-14B)(https://github.com/huggingface/diffusers/pull/11582) -- [SkyReels-v2](https://github.com/SkyworkAI/SkyReels-V2)(https://github.com/huggingface/diffusers/pull/11518) - [Cosmos-Predict2-Video](https://huggingface.co/nvidia/Cosmos-Predict2-2B-Video2World)(https://github.com/huggingface/diffusers/pull/11695) ### Blocked items diff --git a/modules/video_models/models_def.py b/modules/video_models/models_def.py index 4111ee517..c95fe8442 100644 --- a/modules/video_models/models_def.py +++ b/modules/video_models/models_def.py @@ -197,6 +197,18 @@ models = { repo_cls=diffusers.WanImageToVideoPipeline, te_cls=transformers.T5EncoderModel, dit_cls=diffusers.WanTransformer3DModel), + Model(name='WAN 2.1 VACE 1.3B', + url='https://huggingface.co/Wan-AI/Wan2.1-VACE-1.3B-diffusers', + repo='Wan-AI/Wan2.1-VACE-1.3B-diffusers', + repo_cls=diffusers.WanVACEPipeline, + te_cls=transformers.T5EncoderModel, + dit_cls=diffusers.WanTransformer3DModel), + Model(name='WAN 2.1 VACE 14B', + url='https://huggingface.co/Wan-AI/Wan2.1-VACE-14B-diffusers', + repo='Wan-AI/Wan2.1-VACE-14B-diffusers', + repo_cls=diffusers.WanVACEPipeline, + te_cls=transformers.T5EncoderModel, + dit_cls=diffusers.WanTransformer3DModel), ], 'SkyReels V2': [ Model(name='None'),