lllyasviel / lllyasviel/stable-diffusion-webui-forge
GPU Weights setting ignored for first generation
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13k
- Forks
- 1.7k
- PR merge metrics
- No merged PRs in 30d
Description
Hello,
Everytime I start webui forge or change the model and do my **first** generation, the GPU Weights setting seems to be ignored (even when I modify it before to be sure)
The fix I've found is to interupt the generation and start again
`[Low GPU VRAM Warning] Your current GPU free memory is 223.35 MB for this diffusion iteration.`
`[Low GPU VRAM Warning] This number is lower than the safe value of 1536.00 MB.`
`[Low GPU VRAM Warning] If you continue, you may cause NVIDIA GPU performance degradation for this diffusion process, and the speed may be extremely slow (about 10x slower).`
`[Low GPU VRAM Warning] To solve the problem, you can set the 'GPU Weights' (on the top of page) to a lower value.`
`[Low GPU VRAM Warning] If you cannot find 'GPU Weights', you can click the 'all' option in the 'UI' area on the left-top corner of the webpage.`
`[Low GPU VRAM Warning] If you want to take the risk of NVIDIA GPU fallback and test the 10x slower speed, you can (but are highly not recommended to) add '--disable-gpu-warning' to CMD flags to remove this warning.`
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reproducing the first generation after launching the web UI or changing the model, with GPU Weights set explicitly, and compare it with a generation after interruption and retry. The issue provides no file or test entry point; done means the configured GPU Weights value is honored on the first generation and the low-VRAM warning reflects that setting.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100