From 454fa65245447065c078254e7fd3ef63253f487a Mon Sep 17 00:00:00 2001 From: nullquant Date: Thu, 16 May 2024 13:12:16 +0300 Subject: [PATCH] md misprints --- RAUNET.md | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/RAUNET.md b/RAUNET.md index a2bf3fa..ac5f017 100644 --- a/RAUNET.md +++ b/RAUNET.md @@ -1,5 +1,7 @@ During investigation of compatibility issues with [WASasquatch's FreeU_Advanced](https://github.com/WASasquatch/FreeU_Advanced/tree/main) and [blepping's jank HiDiffusion](https://github.com/blepping/comfyui_jankhidiffusion) nodes I stumbled upon some quite hard problems. There are `FreeU` nodes in ComfyUI, but no such for HiDiffusion, so I decided to implement RAUNet on base of my BrushNet implementation. blepping, I am sorry. :) +### RAUNet + What is RAUNet? I know many of you saw and generate images with a lot of limbs, fingers and faces all morphed together. The authors of HiDiffusion invent simple, yet efficient trick to alleviate this problem. Here is an example: @@ -10,7 +12,9 @@ The authors of HiDiffusion invent simple, yet efficient trick to alleviate this The left picture is created using ZavyChromaXL checkpoint on 2048x2048 canvas. The right one using RAUNet. -In my experience the node is helpful but quite sensitive to its parameters. And there is no universal solution - you should adjust them for every new image you generate. It also lowers model's creativity, you usually get only what you described in prompt Look at the example: in first you have a forest in the background, but RAUNet deleted all except fox which is described in the prompt. +In my experience the node is helpful but quite sensitive to its parameters. And there is no universal solution - you should adjust them for every new image you generate. It also lowers model's imagination, you usually get only what you described in prompt. Look at the example: in first you have a forest in the background, but RAUNet deleted all except fox which is described in the prompt. + +### Parameters There are two independent parts in this node: DU (Downsample/Upsample) and XA (CrossAttension). The four parameters are the start and end steps for applying these parts. @@ -20,10 +24,14 @@ The CrossAttension part lowers number of objects which model tracks in image. Usually you apply DU and after several steps apply XA, sometimes you will need only XA, you should try it yourself. +### Compatibility + +It is compatible with BrushNet and most other nodes. + This is ControlNet example. The lower image is pure model, the upper is after using RAUNet. You can see small fox and two tails in lower image. ![example workflow](example/RAUNet2.png?raw=true) [workflow](example/RAUNet_with_CN.json) -The node can be implemented for any model. Right now it can be applyed to SD15 and SDXL models. \ No newline at end of file +The node can be implemented for any model. Right now it can be applied to SD15 and SDXL models. \ No newline at end of file