lllyasviel / lllyasviel/stable-diffusion-webui-forge

text encoder lora unloaded

Open
#1,229 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

Trained a model/concept style on two h100 gpus experimenting with the text encoder,

the lora works on comfyui but it says

lora_te1.text_model.encoder.layers.8.mlp.fc1.lora_a.weight
lora_te1.text_model.encoder.layers.7.mlp.fc1.lora_B.weight

the images work fine

when i try it on forge it unloads it and just inputs a base image, my lora doesn't work.

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 reproducing the reported text-encoder LoRA unload using the model/concept style and the lora_te1 keys listed in the issue, then compare the Forge and ComfyUI behavior. Done means Forge loads the text-encoder LoRA and the generated images reflect it instead of only the base image.

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
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.