sd-forge-layerdiffuse icon indicating copy to clipboard operation
sd-forge-layerdiffuse copied to clipboard

[WIP] Layer Diffusion for WebUI (via Forge)

Results 123 sd-forge-layerdiffuse issues
Sort by recently updated
recently updated
newest added

(AttributeError: 'Linear' object has no attribute 'in_features')Errors occur when I use the realisticVisionV51_v51VAE.safetensors。 `Python 3.11.7 (main, Dec 15 2023, 18:12:31) [GCC 11.2.0] Version: f2.0.1v1.10.1-previous-399-g852e8856 Commit hash: 852e88564c871ef640c12ac053e52234958653d8 Launching Web UI...

Are there any methods to upscale (X2-X4) images with transparency? Hires in different combinations does not work. Any ideas? Thanks!

I tested it on base SDXL models and Pony models, those work for both the attention injection and conv. Switching to Illustirous v1.0, NoobXL, or some merged like WAIIllustrious only...

I tried to make some images this morning and layerdiffuse was working fine as of a few days ago, but now it will not work at all... ![Image](https://github.com/user-attachments/assets/9076b6aa-a66a-4015-af70-ba025bd972dc) this is...

Thanks for your model! I have a job that requires generating a foreground from a background image, but your model currently cannot control the position well and cannot keep harmony...

![image](https://github.com/user-attachments/assets/655f2f86-e2fe-4ee6-8dc3-f34712bd41eb) ![image](https://github.com/user-attachments/assets/8ad8871d-239b-46b9-8065-310655ebcd7f) ![image](https://github.com/user-attachments/assets/14ec456b-bf8f-441a-b648-e43afd7ff49d) pls help me

I think this transparency model has been trained to determine which pixels should be removed when the background color is 50% gray, or when converted to 50% gray in brightness....