Zengtudor/Wan2.1
1
0
Fork 0
mirror of https://github.com/Wan-Video/Wan2.1.git synced 2025-06-17 12:57:40 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Compare commits

base: Zengtudor:a67574e6daf22a46e286a5231ef20a02114daf5c
Branches Tags
Zengtudor:main
Zengtudor:dev/format
Zengtudor:dev/vace_seed
Zengtudor:dev/vace_dev
Zengtudor:dev/vace_size
Zengtudor:dev/vace
...
compare: Zengtudor:1c5a2fd9d4d64e8d60e4199eac36033924a8127d
Branches Tags
Zengtudor:main
Zengtudor:dev/format
Zengtudor:dev/vace_seed
Zengtudor:dev/vace_dev
Zengtudor:dev/vace_size
Zengtudor:dev/vace

3 Commits
a67574e6da ... 1c5a2fd9d4

Author SHA1 Message Date
Zhen Han
1c5a2fd9d4
Merge e649b328e9 into ec902046f6 2025-05-28 15:21:03 +08:00
Shiwei Zhang
ec902046f6
Update README.md 2025-05-27 21:17:16 +08:00
hanzhn
e649b328e9 shrink vace seed range 2025-05-15 13:13:11 +08:00
2 changed files with 3 additions and 3 deletions
Show Stats Expand all files Collapse all files

2
README.md
View File

@ -36,7 +36,7 @@ In this repository, we present **Wan2.1**, a comprehensive and open suite of vid
## Community Works ## Community Works
If your work has improved **Wan2.1** and you would like more people to see it, please inform us. If your work has improved **Wan2.1** and you would like more people to see it, please inform us.
- [Phantom](https://github.com/Phantom-video/Phantom) has developed a unified video generation framework for single and multi-subject references based on **Wan2.1-T2V-1.3B**. Please refer to [their examples](https://github.com/Phantom-video/Phantom). - [Phantom](https://github.com/Phantom-video/Phantom) has developed a unified video generation framework for single and multi-subject references based on both **Wan2.1-T2V-1.3B** and **Wan2.1-T2V-14B**. Please refer to [their examples](https://github.com/Phantom-video/Phantom).
- [UniAnimate-DiT](https://github.com/ali-vilab/UniAnimate-DiT), based on **Wan2.1-14B-I2V**, has trained a Human image animation model and has open-sourced the inference and training code. Feel free to enjoy it! - [UniAnimate-DiT](https://github.com/ali-vilab/UniAnimate-DiT), based on **Wan2.1-14B-I2V**, has trained a Human image animation model and has open-sourced the inference and training code. Feel free to enjoy it!
- [CFG-Zero](https://github.com/WeichenFan/CFG-Zero-star) enhances **Wan2.1** (covering both T2V and I2V models) from the perspective of CFG. - [CFG-Zero](https://github.com/WeichenFan/CFG-Zero-star) enhances **Wan2.1** (covering both T2V and I2V models) from the perspective of CFG.
- [TeaCache](https://github.com/ali-vilab/TeaCache) now supports **Wan2.1** acceleration, capable of increasing speed by approximately 2x. Feel free to give it a try! - [TeaCache](https://github.com/ali-vilab/TeaCache) now supports **Wan2.1** acceleration, capable of increasing speed by approximately 2x. Feel free to give it a try!

4
wan/vace.py
View File

@ -352,7 +352,7 @@ class WanVace(WanT2V):
if n_prompt == "": if n_prompt == "":
n_prompt = self.sample_neg_prompt n_prompt = self.sample_neg_prompt
seed = seed if seed >= 0 else random.randint(0, sys.maxsize) seed = seed if seed >= 0 else random.randint(0, 1e7)
seed_g = torch.Generator(device=self.device) seed_g = torch.Generator(device=self.device)
seed_g.manual_seed(seed) seed_g.manual_seed(seed)
@ -649,7 +649,7 @@ class WanVaceMP(WanVace):
if n_prompt == "": if n_prompt == "":
n_prompt = sample_neg_prompt n_prompt = sample_neg_prompt
seed = seed if seed >= 0 else random.randint(0, sys.maxsize) seed = seed if seed >= 0 else random.randint(0, 1e7)
seed_g = torch.Generator(device=gpu) seed_g = torch.Generator(device=gpu)
seed_g.manual_seed(seed) seed_g.manual_seed(seed)