lllyasviel / lllyasviel/sd-forge-layerdiffuse

no transparency even with sanity check values

Open
#91 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
4.1k
Forks
352
PR merge metrics
No merged PRs in 30d

Description

woman, messy hair, high quality

Negative prompt: bad, ugly

Steps: 20, Sampler: DPM++ 2M SDE Karras, CFG scale: 5, Seed: 12345, Size: 1024x1024, Model hash: 1fe6c7ec54, Model: juggernautXL_version6Rundiffusion, Token merging ratio: 0.2, layerdiffusion_enabled: True, layerdiffusion_method: (SDXL) Only Generate Transparent Image (Attention Injection), layerdiffusion_weight: 1, layerdiffusion_ending_step: 1, layerdiffusion_fg_image: False, layerdiffusion_bg_image: False, layerdiffusion_blend_image: False, layerdiffusion_resize_mode: Crop and Resize, layerdiffusion_fg_additional_prompt: , layerdiffusion_bg_additional_prompt: , layerdiffusion_blend_additional_prompt: , Version: f0.0.12-latest-150-g3cdae096

no transparency whatsoever

![image](https://github.com/layerdiffusion/sd-forge-layerdiffuse/assets/114302238/673b4ec4-cc90-41ae-917a-a6587f083e3b)

the girl looks the same but with a slightly different smily. I wonder why, I copies the generation data and using the juggernautXL checkpoint!

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

Reproduce the report using the supplied prompt, negative prompt, checkpoint, sampler, seed, and LayerDiffuse settings, including “Only Generate Transparent Image.” Compare the result with the expected transparent output and inspect the relevant LayerDiffuse integration point in the Forge WebUI; done means the same settings produce an image with transparency.

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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.