From a3bc00d8565597ce56e57112f1967c95f0ee0a4c Mon Sep 17 00:00:00 2001 From: Extraltodeus Date: Sun, 17 Mar 2024 14:30:00 +0100 Subject: [PATCH] Update README.md --- README.md | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 1ba5238..51c6df4 100644 --- a/README.md +++ b/README.md @@ -8,6 +8,8 @@ The nodes: ## Vector sculptor text encode: +![image](https://github.com/Extraltodeus/Vector_Sculptor_ComfyUI/assets/15731540/06c556f0-537b-4acb-84bf-e0d702c085d0) + Does what I described above. - Sculptor Intensity: How strong the effect will be. If the direction is not reversed I would say that up to 3 you will keep the overall meaning of your prompt. If reversed then don't go above one or face (enjoy?) randomness. @@ -18,6 +20,8 @@ Does what I described above. ## Conditioning (Slerp): +![image](https://github.com/Extraltodeus/Vector_Sculptor_ComfyUI/assets/15731540/36830dc8-47bc-4cd5-abd9-dc9b799fa70f) + Since we are thinking with angles, doing weighted averages might be the reason why things feels so "dilute": ![image](https://github.com/Extraltodeus/Vector_Sculptor_ComfyUI/assets/15731540/89a6d968-717c-492e-a9b1-b360e54d1504) @@ -26,6 +30,8 @@ We're losing magnitude. ## "Conditioning normalize magnitude to empty: +![image](https://github.com/Extraltodeus/Vector_Sculptor_ComfyUI/assets/15731540/57b9bbc4-7581-4fd8-bce3-b1c0d342a42b) + Makes the overall intensity of the conditioning to the one of an empty cond. I have no idea if this is an actually good idea. It tends to give more balanced images regarding the colors and contrasts but also gave me more molten people. If using SDXL the values are worked separately for clip_g and clip_l @@ -35,7 +41,6 @@ If using SDXL the values are worked separately for clip_g and clip_l ### Going towards similar vectors: - ![00859UI_00001_](https://github.com/Extraltodeus/Vector_Sculptor_ComfyUI/assets/15731540/c2fb0adf-0fcb-4cab-9162-fb8a5859173b) "a plate with a few bananas":