Diffusers not working
Hi,
Thank you for the wonderful work!
I met the issue as follows:
"""
The config attributes {'boundary_ratio': 0.9, 'transformer_2': ['diffusers', 'WanTransformer3DModel']} were passed to WanImageToVideoPipeline, but are not expected and will be ignored. Please verify your model_index.json configuration file.
Keyword arguments {'boundary_ratio': 0.9, 'transformer_2': ['diffusers', 'WanTransformer3DModel']} are not expected by WanImageToVideoPipeline and will be ignored.
Loading checkpoint shards: 100%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 12/12 [00:00<00:00, 247.05it/s]
Loading checkpoint shards: 100%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 3/3 [00:03<00:00, 1.03s/it]
Loading pipeline components...: 40%|βββββββββββββββββββββ | 2/5 [00:03<00:04, 1.60s/it]The config attributes {'time_shift_type': 'exponential', 'use_dynamic_shifting': False} were passed to UniPCMultistepScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.
Loading pipeline components...: 100%|ββββββββββββββββββββββββββββββββββββββββββββββββββββ| 5/5 [00:03<00:00, 1.42it/s]
Traceback (most recent call last):
File "D:\AI\Wan2.2\Diffusers.py", line 14, in
pipe = WanImageToVideoPipeline.from_pretrained(model_id, torch_dtype=dtype)
File "D:\AI\Wan2.2\venv\lib\site-packages\huggingface_hub\utils_validators.py", line 114, in _inner_fn
return fn(*args, **kwargs)
File "D:\AI\Wan2.2\venv\lib\site-packages\diffusers\pipelines\pipeline_utils.py", line 1072, in from_pretrained
raise ValueError(
ValueError: Pipeline <class 'diffusers.pipelines.wan.pipeline_wan_i2v.WanImageToVideoPipeline'> expected ['image_encoder', 'image_processor', 'scheduler', 'text_encoder', 'tokenizer', 'transformer', 'vae'], but only {'scheduler', 'transformer', 'vae', 'text_encoder', 'tokenizer'} were passed.
"""
Thank you for your help!
we will merge the PR https://github.com/huggingface/diffusers/pull/12004 soon
for now you need to install from the PR
pip install git+https://github.com/huggingface/diffusers.git@wan2.2
we will merge the PR https://github.com/huggingface/diffusers/pull/12004 soon
for now you need to install from the PR
pip install git+https://github.com/huggingface/diffusers.git@wan2.2
Thank you very much for your timely help. As you suggested, I successfully resolved the issue. I can now run Diffusers smoothly. Wish you a happy life and a successful workοΌ
I am still seeing this issue even after this non-existent branch wan2..2 is already merged to mainline branch.
2025-12-19T16:11:28,619 [INFO ] W-model-1-stdout com.amazonaws.ml.mms.wlm.WorkerLifeCycle - ValueError: Pipeline <class 'diffusers.pipelines.wan.pipeline_wan_i2v.WanImageToVideoPipeline'> expected ['image_encoder', 'image_processor', 'scheduler', 'text_encoder', 'tokenizer', 'transformer', 'vae'], but only {'tokenizer', 'vae', 'transformer', 'text_encoder', 'scheduler'} were passed.
requirements.txt:
torchvision==0.21.0
opencv-python==4.11.0.86
git+https://github.com/huggingface/diffusers.git
transformers
tokenizers
accelerate
peft
ftfy==6.3.1
ffmpeg==1.4
imageio==2.37.2
imageio-ffmpeg==0.6.0
Confirmed that the latest commit is downloaded for diffuser:
2025-12-19T15:53:42,709 [INFO ] W-9000-model-stdout com.amazonaws.ml.mms.wlm.WorkerLifeCycle - Successfully installed anyio-4.12.0 diffusers-0.36.0.dev0 ffmpeg-1.4 ftfy-6.3.1 h11-0.16.0 hf-xet-1.2.0 httpcore-1.0.9 httpx-0.28.1 huggingface-hub-0.36.0 imageio-2.37.2 imageio-ffmpeg-0.6.0
Any help?