lllyasviel / lllyasviel/stable-diffusion-webui-forge

Suggestion: Add an option to generate forever that only renders once a change is made

Open
#2,362 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
13k
Forks
1.7k
PR merge metrics
No merged PRs in 30d

Description

so that you type and it renders

when you stop, so does the rendering

with pc's getting stronger and methods like hyper, LCM, DMD among other distilled models many people can nearly render in real time

comfy's auto queue feature is essentially what i'm after

I would love this feature, it's amazing for testing styles, artist references or loras being able to test things on the fly

edit: guess i just noticed a bug maybe? when in generate forever mode, the render will often stick in the gallery and new images won't populate here, even when stopped and rendering normally, requires a refresh

it's what happens when i have a network hiccup but this seems to induce the issue, can make a new issue for this

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by tracing the existing generate forever mode and the auto queue behavior described in the issue, then inspect how gallery updates are handled. Done means a mode can wait for a change before rendering and the gallery continues to populate correctly after stopping.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai, frontend
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.