ariaotp commited on
Commit
a6c9c33
·
verified ·
1 Parent(s): a9b522e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -6
README.md CHANGED
@@ -2,7 +2,6 @@
2
  tags:
3
  - comfyui
4
  - int8
5
- - booguimage
6
  - qwen2_5_vl
7
  - qwen3
8
  - qwen3_vl
@@ -14,7 +13,6 @@ These models are quantized INT8(both of simple and convrot) for ComfyUI 0.27.0 o
14
 
15
  Original models that I used:
16
 
17
- * Boogu-Image-Edit-Turbo 0708 hotfix: https://huggingface.co/smthem/comfy-org-gguf-int4 (for INT8 version of other types of Boogu-Image, go to https://huggingface.co/Comfy-Org/Boogu-Image instead)
18
  * Qwen2.5-VL 7B (Qwen2.5-VL-7B-Instruct-abliterated): https://huggingface.co/huihui-ai/Qwen2.5-VL-7B-Instruct-abliterated (Needed for Qwen-Image and FireRed-Image-Edit)
19
  * Qwen3 0.6B (Huihui-Qwen3-0.6B-abliterated-v2) : https://huggingface.co/huihui-ai/Huihui-Qwen3-0.6B-abliterated-v2 (Needed for Anima)
20
  * Qwen3 4B (Huihui-Qwen3-4B-abliterated-v2): https://huggingface.co/chinmankokumin/Qwen3-4B-abliterated-v2 (Needed for Z-Image and FLUX.2 Klein 4B)
@@ -23,12 +21,10 @@ Original models that I used:
23
  * Qwen3-VL 4B (Huihui-Qwen3-VL-4B-Instruct-abliterated): https://huggingface.co/ahmed22xa/Huihui-Qwen3-VL-4B-Instruct-abliterated-comfy (Needed for Krea2)
24
  * Qwen3-VL 8B (Huihui-Qwen3-VL-8B-Instruct-abliterated): https://huggingface.co/huihui-ai/Huihui-Qwen3-VL-8B-Instruct-abliterated (Needed for Boogu-Image and Ideogram4)
25
 
26
- For Boogu-Image-Edit-Turbo, Don't used convrot because boogu's attention/feed-forward layer dimensions (840, 3360) are not compatible with ConvRot's group-size requirements (group size must be a power of 4 and evenly divide in_features)
27
-
28
- The rest of them are used Starnodes Model Converter, made by Starnodes2024, quantized from BF16 models https://github.com/Starnodes2024/comfyui-starnodes-modelconverter
29
  Or quant_int8_convrot.py of ComfyUI's official ComfyUI model tools https://github.com/Comfy-Org/comfy-model-tools
30
 
31
  License
32
 
33
- Boogu-Image, Qwen2.5-VL, Qwen3, Qwen3-VL: Apache 2.0
34
  * https://www.apache.org/licenses/LICENSE-2.0.txt
 
2
  tags:
3
  - comfyui
4
  - int8
 
5
  - qwen2_5_vl
6
  - qwen3
7
  - qwen3_vl
 
13
 
14
  Original models that I used:
15
 
 
16
  * Qwen2.5-VL 7B (Qwen2.5-VL-7B-Instruct-abliterated): https://huggingface.co/huihui-ai/Qwen2.5-VL-7B-Instruct-abliterated (Needed for Qwen-Image and FireRed-Image-Edit)
17
  * Qwen3 0.6B (Huihui-Qwen3-0.6B-abliterated-v2) : https://huggingface.co/huihui-ai/Huihui-Qwen3-0.6B-abliterated-v2 (Needed for Anima)
18
  * Qwen3 4B (Huihui-Qwen3-4B-abliterated-v2): https://huggingface.co/chinmankokumin/Qwen3-4B-abliterated-v2 (Needed for Z-Image and FLUX.2 Klein 4B)
 
21
  * Qwen3-VL 4B (Huihui-Qwen3-VL-4B-Instruct-abliterated): https://huggingface.co/ahmed22xa/Huihui-Qwen3-VL-4B-Instruct-abliterated-comfy (Needed for Krea2)
22
  * Qwen3-VL 8B (Huihui-Qwen3-VL-8B-Instruct-abliterated): https://huggingface.co/huihui-ai/Huihui-Qwen3-VL-8B-Instruct-abliterated (Needed for Boogu-Image and Ideogram4)
23
 
24
+ They Starnodes Model Converter, made by Starnodes2024, quantized from BF16 models https://github.com/Starnodes2024/comfyui-starnodes-modelconverter
 
 
25
  Or quant_int8_convrot.py of ComfyUI's official ComfyUI model tools https://github.com/Comfy-Org/comfy-model-tools
26
 
27
  License
28
 
29
+ Qwen2.5-VL, Qwen3, Qwen3-VL: Apache 2.0
30
  * https://www.apache.org/licenses/LICENSE-2.0.txt