Zengtudor/Wan2.1
1
0
Fork 0
mirror of https://github.com/Wan-Video/Wan2.1.git synced 2025-11-04 14:16:57 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

fix messed up

Browse Source
This commit is contained in:
deepbeepmeep 2025-08-11 12:05:18 +02:00
parent 332ca7af0e
commit 58c1549962
3 changed files with 6 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -20,10 +20,12 @@ WanGP supports the Wan (and derived models), Hunyuan Video and LTV Video models
**Follow DeepBeepMeep on Twitter/X to get the Latest News**: https://x.com/deepbeepmeep
## 🔥 Latest Updates :
### August 10 2025: WanGP v7.75 - Faster than the VAE ...
### August 10 2025: WanGP v7.76 - Faster than the VAE ...
We have a funny one here today: FastWan 2.2 5B, the Fastest Video Generator, only 20s to generate 121 frames at 720p. The snag is that VAE is twice as slow...
Thanks to Kijai for extracting the Lora that is used to build the corresponding finetune.
*WanGP 7.76: fixed the messed up I did to i2v models (loras path was wrong for Wan2.2 and Clip broken)*
### August 9 2025: WanGP v7.74 - Qwen Rebirth part 2
Added support for Qwen Lightning lora for a 8 steps generation (https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-8steps-V1.0.safetensors). Lora is not normalized and you can use a multiplier around 0.1.

2
models/wan/any2video.py
View File

@ -97,7 +97,7 @@ class WanAny2V:
device=self.device,
checkpoint_path=os.path.join(checkpoint_dir ,
config.clip_checkpoint),
tokenizer_path=os.path.join(checkpoint_dir , "clip_vit_large_patch14"))
tokenizer_path=os.path.join(checkpoint_dir , "xlm-roberta-large"))
if base_model_type in ["ti2v_2_2"]:

4
wgp.py
View File

@ -53,7 +53,7 @@ AUTOSAVE_FILENAME = "queue.zip"
PROMPT_VARS_MAX = 10
target_mmgp_version = "3.5.8"
WanGP_version = "7.75"
WanGP_version = "7.76"
settings_version = 2.23
max_source_video_frames = 3000
prompt_enhancer_image_caption_model, prompt_enhancer_image_caption_processor, prompt_enhancer_llm_model, prompt_enhancer_llm_tokenizer = None, None, None, None
@ -1620,7 +1620,7 @@ def _parse_args():
def get_lora_dir(model_type):
model_family = get_model_family(model_type)
base_model_type = get_base_model_type(model_type)
i2v = test_class_i2v(model_type) or base_model_type == "i2v_2_2"
i2v = test_class_i2v(model_type) and not base_model_type in ["i2v_2_2", "i2v_2_2_multitalk"]
if model_family == "wan":
lora_dir =args.lora_dir
if i2v and len(lora_dir)==0: