lllyasviel / lllyasviel/stable-diffusion-webui-forge
img2img What latent upscaler is used? No option to change type?
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13k
- Forks
- 1.7k
- PR merge metrics
- No merged PRs in 30d
Description
If a lowres image is generated and HiRes fix is not used at runtime, nor following using the HiRes fix button in the gallery, I had expected to be able to use img2img after the fact.
However, when sending one of the lowres images to img2img during testing the results differ (not in a good way), and I assume that is because the settings aren't exactly the same. There is no dropdown for upscaler and on txt2img generation I'm using Latest (nearest-match), so does this tab use something else?
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 reported difference when a low-resolution image is sent to img2img without HiRes fix, comparing it with txt2img using the “Latest (nearest-match)” upscaler. Trace where the img2img upscaler is selected and determine whether the interface should expose that choice. Done means the upscaler behavior is understood and any needed option or documentation is verified.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100