Merge ca23a2fc59 into ae487cc653

Co-authored-by: Shiwei Zhang <134917139+Steven-SWZhang@users.noreply.github.com>

README.md

@@ -36,6 +36,10 @@ In this repository, we present **Wan2.1**, a comprehensive and open suite of vid
 
 ## Community Works
 If your work has improved **Wan2.1** and you would like more people to see it, please inform us.
+- [Video-As-Prompt](https://github.com/bytedance/Video-As-Prompt), the first unified semantic-controlled video generation model based on **Wan2.1-14B-I2V** with a Mixture-of-Transformers architecture and in-context controls (e.g., concept, style, motion, camera). Refer to the [project page](https://bytedance.github.io/Video-As-Prompt/) for more examples.
+- [LightX2V](https://github.com/ModelTC/LightX2V), a lightweight and efficient video generation framework that integrates **Wan2.1** and **Wan2.2**, supports multiple engineering acceleration techniques for fast inference, which can run on RTX 5090 and RTX 4060 (8GB VRAM).
+- [DriVerse](https://github.com/shalfun/DriVerse), an autonomous driving world model based on **Wan2.1-14B-I2V**, generates future driving videos conditioned on any scene frame and given trajectory. Refer to the [project page](https://github.com/shalfun/DriVerse/tree/main) for more examples.
+- [Training-Free-WAN-Editing](https://github.com/KyujinHan/Awesome-Training-Free-WAN2.1-Editing), built on **Wan2.1-T2V-1.3B**, allows training-free video editing with image-based training-free methods, such as [FlowEdit](https://arxiv.org/abs/2412.08629) and [FlowAlign](https://arxiv.org/abs/2505.23145).
 - [Wan-Move](https://github.com/ali-vilab/Wan-Move), accepted to NeurIPS 2025, a framework that brings **Wan2.1-I2V-14B** to SOTA fine-grained, point-level motion control! Refer to [their project page](https://wan-move.github.io/) for more information.
 - [EchoShot](https://github.com/JoHnneyWang/EchoShot), a native multi-shot portrait video generation model based on **Wan2.1-T2V-1.3B**, allows generation of multiple video clips featuring the same character as well as highly flexible content controllability. Refer to [their project page](https://johnneywang.github.io/EchoShot-webpage/) for more information.
 - [AniCrafter](https://github.com/MyNiuuu/AniCrafter), a human-centric animation model based on **Wan2.1-14B-I2V**, controls the Video Diffusion Models with 3DGS Avatars to insert and animate anyone into any scene following given motion sequences. Refer to the [project page](https://myniuuu.github.io/AniCrafter) for more examples.

wan/modules/attention.py

@@ -107,7 +107,7 @@ def flash_attention(
             max_seqlen_k=lk,
             softmax_scale=softmax_scale,
             causal=causal,
-            deterministic=deterministic)[0].unflatten(0, (b, lq))
+            deterministic=deterministic).unflatten(0, (b, lq))
     else:
         assert FLASH_ATTN_2_AVAILABLE
         x = flash_attn.flash_attn_varlen_func(