chflame163 ComfyUI_OmniGen_Wrapper issues - Githubissues

chflame163 / ComfyUI_OmniGen_Wrapper

ComfyUI custom node of [OmniGen] project.

MIT License

121 stars 4 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Phi3Transformer does not support an attention implementation through torch.nn.functional.scaled_dot_product_attention yet. Please request the support for this architecture: https://github.com/huggingface/transformers/issues/28005. If you believe this error is a bug, please open an issue in Transformers GitHub repository and load your model with the argument `attn_implementation="eager"` meanwhile. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="eager")`

#11 flyricci opened 1 week ago
0
i get this message : dzOmniGenWrapper OmniGen.from_pretrained() got an unexpected keyword argument 'quantize'

#10 ABIA2024 opened 2 weeks ago
0
[Feature Request] Cache to disk instead of only VRAM

#9 guzuligo opened 2 weeks ago
0
A couple of sugestions

#8 set-soft closed 1 week ago
4
开低显存模式下报错

#7 BecarefulW opened 3 weeks ago
4
能把使用torch编译功能吗？

#6 WOAI704 opened 3 weeks ago
0
pip requirements.txt error,Please guide, thank you.

#5 hzeasy opened 3 weeks ago
3
total images must be the same as the number of image tags, got 1 image tags and 2 images

#4 cardenluo opened 3 weeks ago
4
'FrozenDict' object has no attribute 'shift_factor'

#3 miggosec opened 3 weeks ago
3
OmniGen.from_pretrained() got an unexpected keyword argument 'quantize'

#2 TAYLENHE opened 3 weeks ago
1
报错..

#1 msola-ht opened 3 weeks ago
4