-
Does InstantStyle support referencing multiple images with single ip-adapter for img2img pipeline in diffusers or InstantStyle library?
Multiple image-based txt2img works great in diffusers, but no…
-
### Describe the bug
**The `prepare_ip_adapter_image_embeds ` function has a bug that results in unintended feature mixing across images during batch processing. This issue causes the generated ima…
-
### System Info / 系統信息
"orig_height": image_size_x,
"orig_width": image_size_y,
"target_height": image_size_x,
"target_width": image…
ptits updated
2 weeks ago
-
# ComfyUI Error Report
## Error Details
- **Node Type:** MagicClothing_Inpainting
- **Exception Type:** TypeError
- **Exception Message:** For single controlnet: `controlnet_conditioning_scale` mu…
jh248 updated
3 weeks ago
-
原安裝 diffusers 0.11.1 , 將 diffusers 更新至 0.27.0,
按照 https://huggingface.co/docs/diffusers…
-
### Describe the bug
On default settings provided in flux train example readme, with 10 validation images training will error out with out of memory error during validation. on A100 80GB
```
…
-
### Is there an existing issue for this?
- [X] I have searched the existing issues and checked the recent builds/commits of both this extension and the webui
### Is EasyPhoto the latest version?
- …
-
UPDATE - There are simpler repros to fix in the comments below. The one in the first post requires more interaction because of how dataclass and OrderedDict works.
~~~
import diffusers
from diffu…
-
The same issue in instantid node:
> The following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['...']
refer to https://github.com/ZHO-ZHO-ZHO/ComfyUI…
-
is there any work of large-DiT with diffusers ?