CLIPTextEncode CLIP文本编码 RuntimeError：mat1 和 mat2 形状无法相乘（1024x3840 和 1920x4096）
- Dominant language
- Python
- Stars
- 133k
- Forks
- 15.7k
- Avg merge
- 1d 7h
- Merged PRs (30d)
- 158
Description
### Custom Node Testing
- [ ] I have tried disabling custom nodes and the issue persists (see [how to disable custom nodes](https://docs.comfy.org/troubleshooting/custom-node-issues#step-1%3A-test-with-all-custom-nodes-disabled) if you need help)
### Expected Behavior
CLIPTextEncode
CLIP文本编码
RuntimeError：mat1 和 mat2 形状无法相乘（1024x3840 和 1920x4096）
### Actual Behavior
CLIPTextEncode
CLIP文本编码
RuntimeError：mat1 和 mat2 形状无法相乘（1024x3840 和 1920x4096）
### Steps to Reproduce
CLIPTextEncode
CLIP文本编码
RuntimeError：mat1 和 mat2 形状无法相乘（1024x3840 和 1920x4096）
### Debug Logs
```powershell
CLIPTextEncode
CLIP文本编码
RuntimeError：mat1 和 mat2 形状无法相乘（1024x3840 和 1920x4096）
```
### Other
_No response_
Contributor guide
Research direction
The report names only the CLIPTextEncode node and a matrix-shape RuntimeError; no files, tests, or reproducible inputs are provided. First reproduce it with custom nodes disabled and identify the model or configuration producing the 1024x3840 and 1920x4096 shapes. Done means determining the incompatible component and documenting or resolving the failure.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100