WAN2.1 V2版 - 阿里万相2.1视频生成模型，4G显存可用，支持LoRA，支持Teacache加速，支持批量 支持50系显卡 本地一键整合包下载

maya***

老大，看一下这是什么情况，可以启动，但运行就是这样

无言***

maya2024 发表于 2025-4-8 08:09
老大，看一下这是什么情况，可以启动，但运行就是这样

看使用教程，默认只下载了一个1.3B文生视频模型，其他类型生成需要先手动下载模型，再运行。

jerry***

Returning existing local_dir `models\Wan-AI\Wan2.1-I2V-14B-720P` as remote repo cannot be accessed in `snapshot_download` (429 Client Error: Too Many Requests for url: https://hf-mirror.com/api/models/Wan-AI/Wan2.1-I2V-14B-720P/revision/main).

无言***

jerryleee1 发表于 2025-4-8 19:17
Returning existing local_dir `models\Wan-AI\Wan2.1-I2V-14B-720P` as remote repo cannot be accessed i ...

换个时段尝试下载吧，估计是文件太大，服务端拒绝了访问请求

ken***

​ @jasonlee1838  480 下載完成 一樣不行  我把difuserr裡的檔案copy到啟動目錄後 突然1.3b的文生視頻能用了 影生視頻 一樣不行 其他480那些都不能動  all error

无言***

ken7121 发表于 2025-4-9 12:03
​ @jasonlee1838  480 下載完成 一樣不行  我把difuserr裡的檔案copy到啟動目錄後 突然1.3b的文生視頻能用 ...

最近hf-mirror这个镜像流量限制，大文件下载会被限制IP
如果你能科学上网，打开i2v-480.py这个文件，把endpoint='https://hf-mirror.com', 这段代码删了，再执行模型下载就可以了

jerry***

所有模型都下了。但是运行的时候会出错。网页上会出现 connection time out



* 在本地URL上运行:  http://127.0.0.1:7860
* 整合包制作：https://deepface.cc

To create a public link, set `share=True` in `launch()`.
WAN 2.1 14B Image-to-Video 720P
[CMD - DEBUG] Checking if pipeline needs clearing...
[CMD - DEBUG] Pipeline config not changed or pipeline is None. No clearing needed.
[CMD] Loading model: 14B_image_720p with torch dtype: torch.bfloat16 and num_persistent_param_in_dit: 3000000000
Loading models from: models\Wan-AI\Wan2.1-I2V-14B-720P\models_clip_open-clip-xlm-roberta-large-vit-huge-14.pth
    model_name: wan_video_image_encoder model_class: WanImageEncoder
    The following models are loaded: ['wan_video_image_encoder'].
Loading models from: ['models\\Wan-AI\\Wan2.1-I2V-14B-720P\\diffusion_pytorch_model-00001-of-00007.safetensors', 'models\\Wan-AI\\Wan2.1-I2V-14B-720P\\diffusion_pytorch_model-00002-of-00007.safetensors', 'models\\Wan-AI\\Wan2.1-I2V-14B-720P\\diffusion_pytorch_model-00003-of-00007.safetensors', 'models\\Wan-AI\\Wan2.1-I2V-14B-720P\\diffusion_pytorch_model-00004-of-00007.safetensors', 'models\\Wan-AI\\Wan2.1-I2V-14B-720P\\diffusion_pytorch_model-00005-of-00007.safetensors', 'models\\Wan-AI\\Wan2.1-I2V-14B-720P\\diffusion_pytorch_model-00006-of-00007.safetensors', 'models\\Wan-AI\\Wan2.1-I2V-14B-720P\\diffusion_pytorch_model-00007-of-00007.safetensors']
    model_name: wan_video_dit model_class: WanModel
        This model is initialized with extra kwargs: {'has_image_input': True, 'patch_size': [1, 2, 2], 'in_dim': 36, 'dim': 5120, 'ffn_dim': 13824, 'freq_dim': 256, 'text_dim': 4096, 'out_dim': 16, 'num_heads': 40, 'num_layers': 40, 'eps': 1e-06}
Press any key to continue . . .

无言***

jerryleee1 发表于 2025-4-9 16:15
所有模型都下了。但是运行的时候会出错。网页上会出现 connection time out

* 在本地URL上运行:  http://1 ...

1.3B的文生图能用吗？

jerry***

无言以对 发表于 2025-4-9 16:35
1.3B的文生图能用吗？

不能！报错
* 在本地URL上运行:  http://127.0.0.1:7860
* 整合包制作：https://deepface.cc

To create a public link, set `share=True` in `launch()`.
WAN 2.1 1.3B (Text/Video-to-Video)
[CMD - DEBUG] Checking if pipeline needs clearing...
[CMD - DEBUG] Pipeline config not changed or pipeline is None. No clearing needed.
[CMD] Loading model: 1.3B with torch dtype: torch.bfloat16 and num_persistent_param_in_dit: 7000000000
Loading models from: models\Wan-AI\Wan2.1-T2V-1.3B\diffusion_pytorch_model.safetensors
    model_name: wan_video_dit model_class: WanModel
        This model is initialized with extra kwargs: {'has_image_input': False, 'patch_size': [1, 2, 2], 'in_dim': 16, 'dim': 1536, 'ffn_dim': 8960, 'freq_dim': 256, 'text_dim': 4096, 'out_dim': 16, 'num_heads': 12, 'num_layers': 30, 'eps': 1e-06}
    The following models are loaded: ['wan_video_dit'].
Loading models from: models\Wan-AI\Wan2.1-T2V-1.3B\models_t5_umt5-xxl-enc-bf16.pth
    model_name: wan_video_text_encoder model_class: WanTextEncoder
    The following models are loaded: ['wan_video_text_encoder'].
Loading models from: models\Wan-AI\Wan2.1-T2V-1.3B\Wan2.1_VAE.pth
    model_name: wan_video_vae model_class: WanVideoVAE
    The following models are loaded: ['wan_video_vae'].
Using wan_video_text_encoder from models\Wan-AI\Wan2.1-T2V-1.3B\models_t5_umt5-xxl-enc-bf16.pth.
Using wan_video_dit from models\Wan-AI\Wan2.1-T2V-1.3B\diffusion_pytorch_model.safetensors.
Using wan_video_vae from models\Wan-AI\Wan2.1-T2V-1.3B\Wan2.1_VAE.pth.
No wan_video_image_encoder models available.
num_persistent_val 7000000000
[CMD] Model loaded successfully.
Traceback (most recent call last):
  File "E:\Wan2.1-V2\deepface\lib\site-packages\gradio\queueing.py", line 625, in process_events
    response = await route_utils.call_process_api(
  File "E:\Wan2.1-V2\deepface\lib\site-packages\gradio\route_utils.py", line 322, in call_process_api
    output = await app.get_blocks().process_api(
  File "E:\Wan2.1-V2\deepface\lib\site-packages\gradio\blocks.py", line 2137, in process_api
    result = await self.call_function(
  File "E:\Wan2.1-V2\deepface\lib\site-packages\gradio\blocks.py", line 1663, in call_function
    prediction = await anyio.to_thread.run_sync(  # type: ignore
  File "E:\Wan2.1-V2\deepface\lib\site-packages\anyio\to_thread.py", line 56, in run_sync
    return await get_async_backend().run_sync_in_worker_thread(
  File "E:\Wan2.1-V2\deepface\lib\site-packages\anyio\_backends\_asyncio.py", line 2470, in run_sync_in_worker_thread
    return await future
  File "E:\Wan2.1-V2\deepface\lib\site-packages\anyio\_backends\_asyncio.py", line 967, in run
    result = context.run(func, *args)
  File "E:\Wan2.1-V2\deepface\lib\site-packages\gradio\utils.py", line 890, in wrapper
    response = f(*args, **kwargs)
  File "E:\Wan2.1-V2\app.py", line 1315, in generate_videos
    video_data = loaded_pipeline(
  File "E:\Wan2.1-V2\deepface\lib\site-packages\torch\utils\_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
TypeError: WanVideoPipeline.__call__() got an unexpected keyword argument 'cancel_fn'

ken***

无言以对 发表于 2025-4-9 16:35
1.3B的文生图能用吗？

我把diffusion....裡的檔案複製到啟動目錄裡文生視頻1.3b就可以用