https://github.com/huchenlei/ComfyUI_densediffusion
DenseDiffusion custom node for ComfyUI
https://github.com/huchenlei/ComfyUI_densediffusion
Last synced: 4 months ago
JSON representation
DenseDiffusion custom node for ComfyUI
- Host: GitHub
- URL: https://github.com/huchenlei/ComfyUI_densediffusion
- Owner: huchenlei
- License: apache-2.0
- Created: 2024-06-05T01:39:47.000Z (11 months ago)
- Default Branch: main
- Last Pushed: 2024-07-27T18:33:35.000Z (9 months ago)
- Last Synced: 2024-12-12T17:51:23.295Z (4 months ago)
- Language: Python
- Size: 25.4 KB
- Stars: 118
- Watchers: 1
- Forks: 8
- Open Issues: 8
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-comfyui - **ComfyUI DenseDiffusion** - ai/DenseDiffusion) custom node for ComfyUI. (All Workflows Sorted by GitHub Stars)
README
# ComfyUI_densediffusion
DenseDiffusion custom node for ComfyUI. Implements the [DenseDiffusion](https://github.com/naver-ai/DenseDiffusion)-like method for regional prompt used in [Omost](https://github.com/lllyasviel/Omost) project.## What this repo implements
Normal attention calculation can be written as `y=softmax(q@k)@v`. DenseDiffusion introduces the method of attention manipulation on `q@k`, which makes the expression look like `y=softmax(modify(q@k))@v`.
The original DenseDiffusion's implementation does not perform very well according to my testing so here I only implemented the version used in Omost repo. Refer to https://github.com/lllyasviel/Omost#regional-prompter for other regional prompt methods.## How to use
## Limitation [IMPORTANT]
Currently ComfyUI's attention replacements do not compose with each other, so this regional prompt method does not compose with IPAdapter. I am currently working on a universal model patcher to solve this issue.