Merge branch 'huggingface:main' into glm

Author: zRzRzRzRzRzRzR

docs/source/en/_toctree.yml

@@ -290,6 +290,8 @@
         title: CogView4Transformer2DModel
       - local: api/models/dit_transformer2d
         title: DiTTransformer2DModel
+      - local: api/models/easyanimate_transformer3d
+        title: EasyAnimateTransformer3DModel
       - local: api/models/flux_transformer
         title: FluxTransformer2DModel
       - local: api/models/hunyuan_transformer2d
@@ -352,6 +354,8 @@
         title: AutoencoderKLHunyuanVideo
       - local: api/models/autoencoderkl_ltx_video
         title: AutoencoderKLLTXVideo
+      - local: api/models/autoencoderkl_magvit
+        title: AutoencoderKLMagvit
       - local: api/models/autoencoderkl_mochi
         title: AutoencoderKLMochi
       - local: api/models/autoencoder_kl_wan
@@ -430,6 +434,8 @@
       title: DiffEdit
     - local: api/pipelines/dit
       title: DiT
+    - local: api/pipelines/easyanimate
+      title: EasyAnimate
     - local: api/pipelines/flux
       title: Flux
     - local: api/pipelines/control_flux_inpaint

docs/source/en/api/models/autoencoderkl_magvit.md

@@ -0,0 +1,37 @@
+<!--Copyright 2025 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License. -->
+
+# AutoencoderKLMagvit
+
+The 3D variational autoencoder (VAE) model with KL loss used in [EasyAnimate](https://github.com/aigc-apps/EasyAnimate) was introduced by Alibaba PAI.
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import AutoencoderKLMagvit
+
+vae = AutoencoderKLMagvit.from_pretrained("alibaba-pai/EasyAnimateV5.1-12b-zh", subfolder="vae", torch_dtype=torch.float16).to("cuda")
+```
+
+## AutoencoderKLMagvit
+
+[[autodoc]] AutoencoderKLMagvit
+    - decode
+    - encode
+    - all
+
+## AutoencoderKLOutput
+
+[[autodoc]] models.autoencoders.autoencoder_kl.AutoencoderKLOutput
+
+## DecoderOutput
+
+[[autodoc]] models.autoencoders.vae.DecoderOutput

docs/source/en/api/models/easyanimate_transformer3d.md

@@ -0,0 +1,30 @@
+<!--Copyright 2025 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License. -->
+
+# EasyAnimateTransformer3DModel
+
+A Diffusion Transformer model for 3D data from [EasyAnimate](https://github.com/aigc-apps/EasyAnimate) was introduced by Alibaba PAI.
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import EasyAnimateTransformer3DModel
+
+transformer = EasyAnimateTransformer3DModel.from_pretrained("alibaba-pai/EasyAnimateV5.1-12b-zh", subfolder="transformer", torch_dtype=torch.float16).to("cuda")
+```
+
+## EasyAnimateTransformer3DModel
+
+[[autodoc]] EasyAnimateTransformer3DModel
+
+## Transformer2DModelOutput
+
+[[autodoc]] models.modeling_outputs.Transformer2DModelOutput

docs/source/en/api/pipelines/easyanimate.md

@@ -0,0 +1,88 @@
+<!--Copyright 2025 The HuggingFace Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+-->
+
+# EasyAnimate
+[EasyAnimate](https://github.com/aigc-apps/EasyAnimate) by Alibaba PAI.
+
+The description from it's GitHub page:
+*EasyAnimate is a pipeline based on the transformer architecture, designed for generating AI images and videos, and for training baseline models and Lora models for Diffusion Transformer. We support direct prediction from pre-trained EasyAnimate models, allowing for the generation of videos with various resolutions, approximately 6 seconds in length, at 8fps (EasyAnimateV5.1, 1 to 49 frames). Additionally, users can train their own baseline and Lora models for specific style transformations.*
+
+This pipeline was contributed by [bubbliiiing](https://github.com/bubbliiiing). The original codebase can be found [here](https://huggingface.co/alibaba-pai). The original weights can be found under [hf.co/alibaba-pai](https://huggingface.co/alibaba-pai).
+
+There are two official EasyAnimate checkpoints for text-to-video and video-to-video.
+
+| checkpoints | recommended inference dtype |
+|:---:|:---:|
+| [`alibaba-pai/EasyAnimateV5.1-12b-zh`](https://huggingface.co/alibaba-pai/EasyAnimateV5.1-12b-zh) | torch.float16 |
+| [`alibaba-pai/EasyAnimateV5.1-12b-zh-InP`](https://huggingface.co/alibaba-pai/EasyAnimateV5.1-12b-zh-InP) | torch.float16 |
+
+There is one official EasyAnimate checkpoints available for image-to-video and video-to-video.
+
+| checkpoints | recommended inference dtype |
+|:---:|:---:|
+| [`alibaba-pai/EasyAnimateV5.1-12b-zh-InP`](https://huggingface.co/alibaba-pai/EasyAnimateV5.1-12b-zh-InP) | torch.float16 |
+
+There are two official EasyAnimate checkpoints available for control-to-video.
+
+| checkpoints | recommended inference dtype |
+|:---:|:---:|
+| [`alibaba-pai/EasyAnimateV5.1-12b-zh-Control`](https://huggingface.co/alibaba-pai/EasyAnimateV5.1-12b-zh-Control) | torch.float16 |
+| [`alibaba-pai/EasyAnimateV5.1-12b-zh-Control-Camera`](https://huggingface.co/alibaba-pai/EasyAnimateV5.1-12b-zh-Control-Camera) | torch.float16 |
+
+For the EasyAnimateV5.1 series:
+- Text-to-video (T2V) and Image-to-video (I2V) works for multiple resolutions. The width and height can vary from 256 to 1024.
+- Both T2V and I2V models support generation with 1~49 frames and work best at this value. Exporting videos at 8 FPS is recommended.
+
+## Quantization
+
+Quantization helps reduce the memory requirements of very large models by storing model weights in a lower precision data type. However, quantization may have varying impact on video quality depending on the video model.
+
+Refer to the [Quantization](../../quantization/overview) overview to learn more about supported quantization backends and selecting a quantization backend that supports your use case. The example below demonstrates how to load a quantized [`EasyAnimatePipeline`] for inference with bitsandbytes.
+
+```py
+import torch
+from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, EasyAnimateTransformer3DModel, EasyAnimatePipeline
+from diffusers.utils import export_to_video
+
+quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
+transformer_8bit = EasyAnimateTransformer3DModel.from_pretrained(
+    "alibaba-pai/EasyAnimateV5.1-12b-zh",
+    subfolder="transformer",
+    quantization_config=quant_config,
+    torch_dtype=torch.float16,
+)
+
+pipeline = EasyAnimatePipeline.from_pretrained(
+    "alibaba-pai/EasyAnimateV5.1-12b-zh",
+    transformer=transformer_8bit,
+    torch_dtype=torch.float16,
+    device_map="balanced",
+)
+
+prompt = "A cat walks on the grass, realistic style."
+negative_prompt = "bad detailed"
+video = pipeline(prompt=prompt, negative_prompt=negative_prompt, num_frames=49, num_inference_steps=30).frames[0]
+export_to_video(video, "cat.mp4", fps=8)
+```
+
+## EasyAnimatePipeline
+
+[[autodoc]] EasyAnimatePipeline
+  - all
+  - __call__
+
+## EasyAnimatePipelineOutput
+
+[[autodoc]] pipelines.easyanimate.pipeline_output.EasyAnimatePipelineOutput

docs/source/en/using-diffusers/callback.md

@@ -157,6 +157,84 @@ pipeline(
 )
 ```
 
+## IP Adapter Cutoff
+
+IP Adapter is an image prompt adapter that can be used for diffusion models without any changes to the underlying model. We can use the IP Adapter Cutoff Callback to disable the IP Adapter after a certain number of steps. To set up the callback, you need to specify the number of denoising steps after which the callback comes into effect. You can do so by using either one of these two arguments:
+
+- `cutoff_step_ratio`: Float number with the ratio of the steps.
+- `cutoff_step_index`: Integer number with the exact number of the step.
+
+We need to download the diffusion model and load the ip_adapter for it as follows:
+
+```py
+from diffusers import AutoPipelineForText2Image
+from diffusers.utils import load_image
+import torch
+
+pipeline = AutoPipelineForText2Image.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16).to("cuda")
+pipeline.load_ip_adapter("h94/IP-Adapter", subfolder="sdxl_models", weight_name="ip-adapter_sdxl.bin")
+pipeline.set_ip_adapter_scale(0.6)
+```
+The setup for the callback should look something like this:
+
+```py
+
+from diffusers import AutoPipelineForText2Image
+from diffusers.callbacks import IPAdapterScaleCutoffCallback
+from diffusers.utils import load_image
+import torch
+ 
+
+pipeline = AutoPipelineForText2Image.from_pretrained(
+    "stabilityai/stable-diffusion-xl-base-1.0", 
+    torch_dtype=torch.float16
+).to("cuda")
+
+
+pipeline.load_ip_adapter(
+    "h94/IP-Adapter", 
+    subfolder="sdxl_models", 
+    weight_name="ip-adapter_sdxl.bin"
+)
+
+pipeline.set_ip_adapter_scale(0.6)
+
+
+callback = IPAdapterScaleCutoffCallback(
+    cutoff_step_ratio=None, 
+    cutoff_step_index=5
+)
+
+image = load_image(
+    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/ip_adapter_diner.png"
+)
+
+generator = torch.Generator(device="cuda").manual_seed(2628670641)
+
+images = pipeline(
+    prompt="a tiger sitting in a chair drinking orange juice",
+    ip_adapter_image=image,
+    negative_prompt="deformed, ugly, wrong proportion, low res, bad anatomy, worst quality, low quality",
+    generator=generator,
+    num_inference_steps=50,
+    callback_on_step_end=callback,
+).images
+
+images[0].save("custom_callback_img.png")
+```
+
+<div class="flex gap-4">
+  <div>
+    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/without_callback.png" alt="generated image of a tiger sitting in a chair drinking orange juice" />
+    <figcaption class="mt-2 text-center text-sm text-gray-500">without IPAdapterScaleCutoffCallback</figcaption>
+  </div>
+  <div>
+    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/with_callback2.png" alt="generated image of a tiger sitting in a chair drinking orange juice with ip adapter callback" />
+    <figcaption class="mt-2 text-center text-sm text-gray-500">with IPAdapterScaleCutoffCallback</figcaption>
+  </div>
+</div>
+
+
 ## Display image after each generation step
 
 > [!TIP]

src/diffusers/__init__.py

@@ -94,6 +94,7 @@
             "AutoencoderKLCogVideoX",
             "AutoencoderKLHunyuanVideo",
             "AutoencoderKLLTXVideo",
+            "AutoencoderKLMagvit",
             "AutoencoderKLMochi",
             "AutoencoderKLTemporalDecoder",
             "AutoencoderKLWan",
@@ -109,6 +110,7 @@
             "ControlNetUnionModel",
             "ControlNetXSAdapter",
             "DiTTransformer2DModel",
+            "EasyAnimateTransformer3DModel",
             "FluxControlNetModel",
             "FluxMultiControlNetModel",
             "FluxTransformer2DModel",
@@ -293,6 +295,9 @@
             "CogView4Pipeline",
             "ConsisIDPipeline",
             "CycleDiffusionPipeline",
+            "EasyAnimateControlPipeline",
+            "EasyAnimateInpaintPipeline",
+            "EasyAnimatePipeline",
             "FluxControlImg2ImgPipeline",
             "FluxControlInpaintPipeline",
             "FluxControlNetImg2ImgPipeline",
@@ -620,6 +625,7 @@
             AutoencoderKLCogVideoX,
             AutoencoderKLHunyuanVideo,
             AutoencoderKLLTXVideo,
+            AutoencoderKLMagvit,
             AutoencoderKLMochi,
             AutoencoderKLTemporalDecoder,
             AutoencoderKLWan,
@@ -635,6 +641,7 @@
             ControlNetUnionModel,
             ControlNetXSAdapter,
             DiTTransformer2DModel,
+            EasyAnimateTransformer3DModel,
             FluxControlNetModel,
             FluxMultiControlNetModel,
             FluxTransformer2DModel,
@@ -798,6 +805,9 @@
             CogView4Pipeline,
             ConsisIDPipeline,
             CycleDiffusionPipeline,
+            EasyAnimateControlPipeline,
+            EasyAnimateInpaintPipeline,
+            EasyAnimatePipeline,
             FluxControlImg2ImgPipeline,
             FluxControlInpaintPipeline,
             FluxControlNetImg2ImgPipeline,

src/diffusers/loaders/single_file_utils.py

@@ -1448,8 +1448,8 @@ def convert_open_clip_checkpoint(
 
     if text_proj_key in checkpoint:
         text_proj_dim = int(checkpoint[text_proj_key].shape[0])
-    elif hasattr(text_model.config, "projection_dim"):
-        text_proj_dim = text_model.config.projection_dim
+    elif hasattr(text_model.config, "hidden_size"):
+        text_proj_dim = text_model.config.hidden_size
     else:
         text_proj_dim = LDM_OPEN_CLIP_TEXT_PROJECTION_DIM
 

src/diffusers/models/__init__.py

@@ -33,6 +33,7 @@
     _import_structure["autoencoders.autoencoder_kl_cogvideox"] = ["AutoencoderKLCogVideoX"]
     _import_structure["autoencoders.autoencoder_kl_hunyuan_video"] = ["AutoencoderKLHunyuanVideo"]
     _import_structure["autoencoders.autoencoder_kl_ltx"] = ["AutoencoderKLLTXVideo"]
+    _import_structure["autoencoders.autoencoder_kl_magvit"] = ["AutoencoderKLMagvit"]
     _import_structure["autoencoders.autoencoder_kl_mochi"] = ["AutoencoderKLMochi"]
     _import_structure["autoencoders.autoencoder_kl_temporal_decoder"] = ["AutoencoderKLTemporalDecoder"]
     _import_structure["autoencoders.autoencoder_kl_wan"] = ["AutoencoderKLWan"]
@@ -72,6 +73,7 @@
     _import_structure["transformers.transformer_allegro"] = ["AllegroTransformer3DModel"]
     _import_structure["transformers.transformer_cogview3plus"] = ["CogView3PlusTransformer2DModel"]
     _import_structure["transformers.transformer_cogview4"] = ["CogView4Transformer2DModel"]
+    _import_structure["transformers.transformer_easyanimate"] = ["EasyAnimateTransformer3DModel"]
     _import_structure["transformers.transformer_flux"] = ["FluxTransformer2DModel"]
     _import_structure["transformers.transformer_hunyuan_video"] = ["HunyuanVideoTransformer3DModel"]
     _import_structure["transformers.transformer_ltx"] = ["LTXVideoTransformer3DModel"]
@@ -109,6 +111,7 @@
             AutoencoderKLCogVideoX,
             AutoencoderKLHunyuanVideo,
             AutoencoderKLLTXVideo,
+            AutoencoderKLMagvit,
             AutoencoderKLMochi,
             AutoencoderKLTemporalDecoder,
             AutoencoderKLWan,
@@ -144,6 +147,7 @@
             ConsisIDTransformer3DModel,
             DiTTransformer2DModel,
             DualTransformer2DModel,
+            EasyAnimateTransformer3DModel,
             FluxTransformer2DModel,
             HunyuanDiT2DModel,
             HunyuanVideoTransformer3DModel,

src/diffusers/models/attention_processor.py

@@ -274,7 +274,10 @@ def __init__(
             self.to_add_out = None
 
         if qk_norm is not None and added_kv_proj_dim is not None:
-            if qk_norm == "fp32_layer_norm":
+            if qk_norm == "layer_norm":
+                self.norm_added_q = nn.LayerNorm(dim_head, eps=eps, elementwise_affine=elementwise_affine)
+                self.norm_added_k = nn.LayerNorm(dim_head, eps=eps, elementwise_affine=elementwise_affine)
+            elif qk_norm == "fp32_layer_norm":
                 self.norm_added_q = FP32LayerNorm(dim_head, elementwise_affine=False, bias=False, eps=eps)
                 self.norm_added_k = FP32LayerNorm(dim_head, elementwise_affine=False, bias=False, eps=eps)
             elif qk_norm == "rms_norm":

src/diffusers/models/autoencoders/__init__.py

@@ -5,6 +5,7 @@
 from .autoencoder_kl_cogvideox import AutoencoderKLCogVideoX
 from .autoencoder_kl_hunyuan_video import AutoencoderKLHunyuanVideo
 from .autoencoder_kl_ltx import AutoencoderKLLTXVideo
+from .autoencoder_kl_magvit import AutoencoderKLMagvit
 from .autoencoder_kl_mochi import AutoencoderKLMochi
 from .autoencoder_kl_temporal_decoder import AutoencoderKLTemporalDecoder
 from .autoencoder_kl_wan import AutoencoderKLWan