Upload folder using huggingface_hub

.gitattributes

@@ -34,3 +34,10 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 google/umt5-xxl/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+assets/comp_effic.png filter=lfs diff=lfs merge=lfs -text
+assets/data_for_diff_stage.jpg filter=lfs diff=lfs merge=lfs -text
+assets/i2v_res.png filter=lfs diff=lfs merge=lfs -text
+assets/t2v_res.jpg filter=lfs diff=lfs merge=lfs -text
+assets/vben_vs_sota.png filter=lfs diff=lfs merge=lfs -text
+assets/video_dit_arch.jpg filter=lfs diff=lfs merge=lfs -text
+assets/video_vae_res.jpg filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,13 +1,5 @@
----
-license: apache-2.0
-language:
-- en
-- zh
-tags:
-- video generation
----
 # Wan2.1
- 
+
 <p align="center">
     <img src="assets/logo.png" width="400"/>
 <p>
@@ -522,14 +514,10 @@ torchrun --nproc_per_node=8 generate.py --task vace-14B --size 1280*720 --ckpt_d
 ```
 
 ##### (3) Running local gradio
-- Single-GPU inference
-```sh
-python gradio/vace.py --ckpt_dir ./Wan2.1-VACE-1.3B
-```
 
-- Multi-GPU inference using FSDP + xDiT USP
 ```sh
-python gradio/vace.py --mp --ulysses_size 8 --ckpt_dir ./Wan2.1-VACE-14B/
+cd gradio
+python vace_1.3B_singleGPU.py --ckpt_dir_720p ./Wan2.1-VACE-1.3B  # use 480P model in gradio
 ```
 
 #### Run Text-to-Image Generation