Improve model card: Update pipeline_tag, add library_name, and include NABLA paper details

README.md

@@ -1,15 +1,16 @@
 ---
-license: apache-2.0
 language:
 - en
 - zh
+license: apache-2.0
+pipeline_tag: any-to-any
 tags:
 - video generation
 - video-to-video editing
 - refernce-to-video
-
-pipeline_tag: image-to-video
+library_name: diffusers
 ---
+
 # Wan2.1
 
 <p align="center">
@@ -31,6 +32,17 @@ In this repository, we present **Wan2.1**, a comprehensive and open suite of vid
 - 👍 **Visual Text Generation**: **Wan2.1** is the first video model capable of generating both Chinese and English text, featuring robust text generation that enhances its practical applications.
 - 👍 **Powerful Video VAE**: **Wan-VAE** delivers exceptional efficiency and performance, encoding and decoding 1080P videos of any length while preserving temporal information, making it an ideal foundation for video and image generation.
 
+## $
+abla$NABLA: Neighborhood Adaptive Block-Level Attention
+
+The **Wan2.1** model incorporates advanced attention mechanisms, including those detailed in the paper [$
+abla$NABLA: Neighborhood Adaptive Block-Level Attention](https://huggingface.co/papers/2507.13546).
+
+The abstract of the paper is the following:
+"Recent progress in transformer-based architectures has demonstrated remarkable success in video generation tasks. However, the quadratic complexity of full attention mechanisms remains a critical bottleneck, particularly for high-resolution and long-duration video sequences. In this paper, we propose NABLA, a novel Neighborhood Adaptive Block-Level Attention mechanism that dynamically adapts to sparsity patterns in video diffusion transformers (DiTs). By leveraging block-wise attention with adaptive sparsity-driven threshold, NABLA reduces computational overhead while preserving generative quality. Our method does not require custom low-level operator design and can be seamlessly integrated with PyTorch's Flex Attention operator. Experiments demonstrate that NABLA achieves up to 2.7x faster training and inference compared to baseline almost without compromising quantitative metrics (CLIP score, VBench score, human evaluation score) and visual quality drop."
+
+This technique contributes to the efficiency and performance of video generation within the Wan2.1 framework.
+
 ## Video Demos
 
 <div align="center">
@@ -106,18 +118,18 @@ pip install -r requirements.txt
 
 #### Model Download
 
-| Models       | Download Link                                                                                                                                           |    Notes                      |
-|--------------|---------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------|
-| T2V-14B      | 🤗 [Huggingface](https://huggingface.co/Wan-AI/Wan2.1-T2V-14B)      🤖 [ModelScope](https://www.modelscope.cn/models/Wan-AI/Wan2.1-T2V-14B)             | Supports both 480P and 720P
-| I2V-14B-720P | 🤗 [Huggingface](https://huggingface.co/Wan-AI/Wan2.1-I2V-14B-720P)    🤖 [ModelScope](https://www.modelscope.cn/models/Wan-AI/Wan2.1-I2V-14B-720P)     | Supports 720P
-| I2V-14B-480P | 🤗 [Huggingface](https://huggingface.co/Wan-AI/Wan2.1-I2V-14B-480P)    🤖 [ModelScope](https://www.modelscope.cn/models/Wan-AI/Wan2.1-I2V-14B-480P)     | Supports 480P
-| T2V-1.3B     | 🤗 [Huggingface](https://huggingface.co/Wan-AI/Wan2.1-T2V-1.3B)     🤖 [ModelScope](https://www.modelscope.cn/models/Wan-AI/Wan2.1-T2V-1.3B)            | Supports 480P
-| FLF2V-14B    | 🤗 [Huggingface](https://huggingface.co/Wan-AI/Wan2.1-FLF2V-14B-720P)     🤖 [ModelScope](https://www.modelscope.cn/models/Wan-AI/Wan2.1-FLF2V-14B-720P) | Supports 720P
-| VACE-1.3B    | 🤗 [Huggingface](https://huggingface.co/Wan-AI/Wan2.1-VACE-1.3B)     🤖 [ModelScope](https://www.modelscope.cn/models/Wan-AI/Wan2.1-VACE-1.3B)          | Supports 480P
-| VACE-14B     | 🤗 [Huggingface](https://huggingface.co/Wan-AI/Wan2.1-VACE-14B)     🤖 [ModelScope](https://www.modelscope.cn/models/Wan-AI/Wan2.1-VACE-14B)        | Supports both 480P and 720P
-
-> 💡Note: 
-> * The 1.3B model is capable of generating videos at 720P resolution. However, due to limited training at this resolution, the results are generally less stable compared to 480P. For optimal performance, we recommend using 480P resolution. 
+| Models | Download Link | Notes |
+|---|---|---|
+| T2V-14B | 🤗 [Huggingface](https://huggingface.co/Wan-AI/Wan2.1-T2V-14B) 🤖 [ModelScope](https://www.modelscope.cn/models/Wan-AI/Wan2.1-T2V-14B) | Supports both 480P and 720P
+| I2V-14B-720P | 🤗 [Huggingface](https://huggingface.co/Wan-AI/Wan2.1-I2V-14B-720P) 🤖 [ModelScope](https://www.modelscope.cn/models/Wan-AI/Wan2.1-I2V-14B-720P) | Supports 720P
+| I2V-14B-480P | 🤗 [Huggingface](https://huggingface.co/Wan-AI/Wan2.1-I2V-14B-480P) 🤖 [ModelScope](https://www.modelscope.cn/models/Wan-AI/Wan2.1-I2V-14B-480P) | Supports 480P
+| T2V-1.3B | 🤗 [Huggingface](https://huggingface.co/Wan-AI/Wan2.1-T2V-1.3B) 🤖 [ModelScope](https://www.modelscope.cn/models/Wan-AI/Wan2.1-T2V-1.3B) | Supports 480P
+| FLF2V-14B | 🤗 [Huggingface](https://huggingface.co/Wan-AI/Wan2.1-FLF2V-14B-720P) 🤖 [ModelScope](https://www.modelscope.cn/models/Wan-AI/Wan2.1-FLF2V-14B-720P) | Supports 720P
+| VACE-1.3B | 🤗 [Huggingface](https://huggingface.co/Wan-AI/Wan2.1-VACE-1.3B) 🤖 [ModelScope](https://www.modelscope.cn/models/Wan-AI/Wan2.1-VACE-1.3B) | Supports 480P
+| VACE-14B | 🤗 [Huggingface](https://huggingface.co/Wan-AI/Wan2.1-VACE-14B) 🤖 [ModelScope](https://www.modelscope.cn/models/Wan-AI/Wan2.1-VACE-14B) | Supports both 480P and 720P
+
+> 💡Note:
+> * The 1.3B model is capable of generating videos at 720P resolution. However, due to limited training at this resolution, the results are generally less stable compared to 480P. For optimal performance, we recommend using 480P resolution.
 > * For the first-last frame to video generation, we train our model primarily on Chinese text-video pairs. Therefore, we recommend using Chinese prompt to achieve better results.
 
 
@@ -190,7 +202,7 @@ python generate.py  --task t2v-1.3B --size 832*480 --ckpt_dir ./Wan2.1-T2V-1.3B
 
   * Ulysess Strategy
 
-    If you want to use [`Ulysses`](https://arxiv.org/abs/2309.14509) strategy, you should set `--ulysses_size $GPU_NUMS`. Note that the `num_heads` should be divisible by `ulysses_size` if you wish to use `Ulysess` strategy. For the 1.3B model, the `num_heads` is `12` which can't be divided by 8 (as most multi-GPU machines have 8 GPUs). Therefore, it is recommended to use `Ring Strategy` instead.
+    If you want to use [`Ulysses`](https://arxiv.org/abs/2309.14509) strategy, you should set `--ulysses_size $GPU_NUMS`. Note that the `num_heads` should be divisible by `ulysses_size` if you wish to use `Ulyess` strategy. For the 1.3B model, the `num_heads` is `12` which can't be divided by 8 (as most multi-GPU machines have 8 GPUs). Therefore, it is recommended to use `Ring Strategy` instead.
 
   * Ring Strategy
 
@@ -611,7 +623,7 @@ We test the computational efficiency of different **Wan2.1** models on different
 
 ## Introduction of Wan2.1
 
-**Wan2.1**  is designed on the mainstream diffusion transformer paradigm, achieving significant advancements in generative capabilities through a series of innovations. These include our novel spatio-temporal variational autoencoder (VAE), scalable training strategies, large-scale data construction, and automated evaluation metrics. Collectively, these contributions enhance the model’s performance and versatility.
+**Wan2.1** is designed on the mainstream diffusion transformer paradigm, achieving significant advancements in generative capabilities through a series of innovations. These include our novel spatio-temporal variational autoencoder (VAE), scalable training strategies, large-scale data construction, and automated evaluation metrics. Collectively, these contributions enhance the model’s performance and versatility.
 
 
 ##### (1) 3D Variational Autoencoders
@@ -632,10 +644,10 @@ We propose a novel 3D causal VAE architecture, termed **Wan-VAE** specifically d
 </div>
 
 
-| Model  | Dimension | Input Dimension | Output Dimension | Feedforward Dimension | Frequency Dimension | Number of Heads | Number of Layers |
-|--------|-----------|-----------------|------------------|-----------------------|---------------------|-----------------|------------------|
-| 1.3B   | 1536      | 16              | 16               | 8960                  | 256                 | 12              | 30               |
-| 14B   | 5120       | 16              | 16               | 13824                 | 256                 | 40              | 40               |
+| Model | Dimension | Input Dimension | Output Dimension | Feedforward Dimension | Frequency Dimension | Number of Heads | Number of Layers |
+|---|---|---|---|---|---|---|---|
+| 1.3B | 1536 | 16 | 16 | 8960 | 256 | 12 | 30 |
+| 14B | 5120 | 16 | 16 | 13824 | 256 | 40 | 40 |