diff --git a/docs/diffusers/installation.md b/docs/diffusers/installation.md index d0f9ad2fa3..c32c624947 100644 --- a/docs/diffusers/installation.md +++ b/docs/diffusers/installation.md @@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License. # Installation -🤗 Diffusers is tested on Python 3.8+, MindSpore 2.2.10+. Follow the installation instructions below for the deep learning library you are using: +🤗 Diffusers is tested on Python 3.8+, MindSpore 2.3+. Follow the installation instructions below for the deep learning library you are using: - [MindSpore](https://www.mindspore.cn/install) installation instructions diff --git a/docs/diffusers/limitations.md b/docs/diffusers/limitations.md index 30b6153c71..c6312eafb3 100644 --- a/docs/diffusers/limitations.md +++ b/docs/diffusers/limitations.md @@ -58,7 +58,6 @@ The table below represents the current support in mindone/diffusers for each of The table below represents the current support in mindone/diffusers for each of those pipelines in **MindSpore 2.3.0**, whether they have support in Pynative fp16 mode, Graph fp16 mode, Pynative fp32 mode or Graph fp32 mode. -> Hint: Due to the precision issue with GroupNorm affecting almost all pipelines under FP16, leading to inference > precision issues of pipelines, the experiments in the table below default to upcasting GroupNorm to FP32 to avoid > this issue. diff --git a/mindone/diffusers/__init__.py b/mindone/diffusers/__init__.py index 772c1f3611..25a995e641 100644 --- a/mindone/diffusers/__init__.py +++ b/mindone/diffusers/__init__.py @@ -1,4 +1,4 @@ -__version__ = "0.27.1" +__version__ = "0.29.2" from typing import TYPE_CHECKING @@ -13,6 +13,7 @@ _import_structure = { "configuration_utils": ["ConfigMixin"], + "loaders": ["FromOriginalModelMixin"], "models": [ "AsymmetricAutoencoderKL", "AutoencoderKL", @@ -20,21 +21,28 @@ "AutoencoderTiny", "ConsistencyDecoderVAE", "ControlNetModel", + "ControlNetXSAdapter", + "DiTTransformer2DModel", + "HunyuanDiT2DModel", "I2VGenXLUNet", "Kandinsky3UNet", "ModelMixin", "MotionAdapter", "MultiAdapter", + "PixArtTransformer2DModel", "PriorTransformer", + "SD3ControlNetModel", + "SD3MultiControlNetModel", + "SD3Transformer2DModel", "T2IAdapter", "T5FilmDecoder", "Transformer2DModel", - "SD3Transformer2DModel", "StableCascadeUNet", "UNet1DModel", "UNet2DConditionModel", "UNet2DModel", "UNet3DConditionModel", + "UNetControlNetXSModel", "UNetMotionModel", "UNetSpatioTemporalConditionModel", "UVit2DModel", @@ -51,6 +59,7 @@ ], "pipelines": [ "AnimateDiffPipeline", + "AnimateDiffSDXLPipeline", "AnimateDiffVideoToVideoPipeline", "BlipDiffusionControlNetPipeline", "BlipDiffusionPipeline", @@ -60,6 +69,7 @@ "DDPMPipeline", "DiffusionPipeline", "DiTPipeline", + "HunyuanDiTPipeline", "I2VGenXLPipeline", "IFImg2ImgPipeline", "IFImg2ImgSuperResolutionPipeline", @@ -90,17 +100,23 @@ "LatentConsistencyModelPipeline", "LDMSuperResolutionPipeline", "LDMTextToImagePipeline", + "MarigoldDepthPipeline", + "MarigoldNormalsPipeline", "PixArtAlphaPipeline", + "PixArtSigmaPipeline", "ShapEImg2ImgPipeline", "ShapEPipeline", "StableCascadeCombinedPipeline", "StableCascadeDecoderPipeline", "StableCascadePriorPipeline", + "StableDiffusion3ControlNetPipeline", + "StableDiffusion3Img2ImgPipeline", "StableDiffusion3Pipeline", "StableDiffusionAdapterPipeline", "StableDiffusionControlNetImg2ImgPipeline", "StableDiffusionControlNetInpaintPipeline", "StableDiffusionControlNetPipeline", + "StableDiffusionControlNetXSPipeline", "StableDiffusionDepth2ImgPipeline", "StableDiffusionDiffEditPipeline", "StableDiffusionGLIGENPipeline", @@ -116,6 +132,7 @@ "StableDiffusionXLControlNetImg2ImgPipeline", "StableDiffusionXLControlNetInpaintPipeline", "StableDiffusionXLControlNetPipeline", + "StableDiffusionXLControlNetXSPipeline", "StableDiffusionXLImg2ImgPipeline", "StableDiffusionXLInpaintPipeline", "StableDiffusionXLInstructPix2PixPipeline", @@ -172,12 +189,18 @@ AutoencoderTiny, ConsistencyDecoderVAE, ControlNetModel, + ControlNetXSAdapter, + DiTTransformer2DModel, + HunyuanDiT2DModel, I2VGenXLUNet, Kandinsky3UNet, ModelMixin, MotionAdapter, MultiAdapter, + PixArtTransformer2DModel, PriorTransformer, + SD3ControlNetModel, + SD3MultiControlNetModel, SD3Transformer2DModel, StableCascadeUNet, T2IAdapter, @@ -187,6 +210,7 @@ UNet2DConditionModel, UNet2DModel, UNet3DConditionModel, + UNetControlNetXSModel, UNetMotionModel, UNetSpatioTemporalConditionModel, UVit2DModel, @@ -203,6 +227,7 @@ ) from .pipelines import ( AnimateDiffPipeline, + AnimateDiffSDXLPipeline, AnimateDiffVideoToVideoPipeline, BlipDiffusionControlNetPipeline, BlipDiffusionPipeline, @@ -211,6 +236,7 @@ DDPMPipeline, DiffusionPipeline, DiTPipeline, + HunyuanDiTPipeline, I2VGenXLPipeline, IFImg2ImgPipeline, IFImg2ImgSuperResolutionPipeline, @@ -241,17 +267,23 @@ LatentConsistencyModelPipeline, LDMSuperResolutionPipeline, LDMTextToImagePipeline, + MarigoldDepthPipeline, + MarigoldNormalsPipeline, PixArtAlphaPipeline, + PixArtSigmaPipeline, ShapEImg2ImgPipeline, ShapEPipeline, StableCascadeCombinedPipeline, StableCascadeDecoderPipeline, StableCascadePriorPipeline, + StableDiffusion3ControlNetPipeline, + StableDiffusion3Img2ImgPipeline, StableDiffusion3Pipeline, StableDiffusionAdapterPipeline, StableDiffusionControlNetImg2ImgPipeline, StableDiffusionControlNetInpaintPipeline, StableDiffusionControlNetPipeline, + StableDiffusionControlNetXSPipeline, StableDiffusionDepth2ImgPipeline, StableDiffusionDiffEditPipeline, StableDiffusionGLIGENPipeline, @@ -267,6 +299,7 @@ StableDiffusionXLControlNetImg2ImgPipeline, StableDiffusionXLControlNetInpaintPipeline, StableDiffusionXLControlNetPipeline, + StableDiffusionXLControlNetXSPipeline, StableDiffusionXLImg2ImgPipeline, StableDiffusionXLInpaintPipeline, StableDiffusionXLInstructPix2PixPipeline,