Check out the SD-WebUI extension for more information.
This extension enables large image drawing & upscaling with limited VRAM via the following techniques:
- Reproduced SOTA Tiled Diffusion methods
- pkuliyi2015 & Kahsolt's Tiled VAE algorithm
pkuliyi2015 & Kahsolt's TIled Noise Inversion method
Note
Sizes/dimensions are in pixels and then converted to latent-space sizes.
- Supported models
- SD1.x, SD2.x, SDXL, SD3
- FLUX
- ControlNet support
-
StableSR support -
Tiled Noise Inversion - Tiled VAE
- Regional Prompt Control
- Img2img upscale
- Ultra-Large image generation
Tip
- Set
tile_overlapto 0 anddenoiseto 1 to see the tile seams and then adjust the options to your needs. - Increase
tile_batch_sizeto increase speed (if your machine can handle it). - Use the colorfix node if your colors look off.
| Name | Description |
|---|---|
method |
Tiling strategy. |
tile_width |
Tile's width |
tile_height |
Tile's height |
tile_overlap |
Tile's overlap |
tile_batch_size |
The number of tiles to process in a batch |
If you have the Math Expression node (or something similar), you can use that to pass in the latent that's passed in your KSampler and divide the tile_height/tile_width by the number of rows/columns you want.
C = number of columns you want
R = number of rows you want
pixel width of input image or latent // C = tile_width
pixel height of input image or latent // R = tile_height
A tiling algorithm that attempts to eliminate seams by randomly shifting the denoise window per timestep. It is mainly used for fast inferences by setting tile_overlap to 0; otherwise, it's better to stick with the other tiling strategies as they produce better outputs.
This additional feature is experimental, in testing, and subject to change.
The recommended tile sizes are given upon the creation of the node based on the available VRAM.
Note
Enabling fast for the decoder may produce images with slightly higher contrast and brightness.
| Name | Description |
|---|---|
tile_size |
The image is split into tiles, which are then padded with 11/32 pixels' in the decoder/encoder. |
fast |
|
color_fix |
Only estimate GroupNorm before downsampling, i.e., run in a semi-fast mode. Only for the encoder. Can restore colors if tiles are too small. |
The following images can be loaded in ComfyUI.
Simple upscale.
4x upscale. 3 passes.
Great thanks to all the contributors! 🎉🎉🎉
The implementation of MultiDiffusion, Mixture of Diffusers, and Tiled VAE code is currently under Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License since it was borrowed from the wonderful SD-WebUI extension. Anything else GPLv3.
@article{jimenez2023mixtureofdiffusers,
title={Mixture of Diffusers for scene composition and high resolution image generation},
author={Álvaro Barbero Jiménez},
journal={arXiv preprint arXiv:2302.02412},
year={2023}
}@article{bar2023multidiffusion,
title={MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation},
author={Bar-Tal, Omer and Yariv, Lior and Lipman, Yaron and Dekel, Tali},
journal={arXiv preprint arXiv:2302.08113},
year={2023}
}