lllyasviel / lllyasviel/stable-diffusion-webui-forge

how to change photomaker2 default sdxl model? and how to make it load sdxl model from exiting models in forge models folder instead of downloading a new model

Open
#1,564 2 comments 2 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

Peace, new Spaces feature in forge is very brilliant and very needed, hope we get more new spaces options, another thing we need the ability to choose models download option like to choose don't download the default model and choose another models form already downloaded models by user, like in my request here when i choose to install photomaker2 in forge i noticed that it's downloading "diffusion_pytorch_model.fp16.safetensor 5.14G" which i think is some version of sdxl model, i tried photomaker2 demo online, the results were good, but i noticed it could be better if we used another sdxl models with it, so i hope you add an option to don't download the default sdxl model and load all available sdxl models in forge models folder, and add option like drop menu to choose between them, this will be really amazing, second thing i was hope there is way to use other ControlNets combined with photomaker2 like open pose..... etc, so i hope you add this amazing option?????

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 how the Photomaker2 Space installs its default SDXL model and discovers models in the Forge models folder. Then inspect where model selection and ControlNet support are exposed. Done would mean reusing selected existing SDXL models, avoiding an unnecessary default download, and supporting the requested ControlNet combinations.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.