spooknik commited on
Commit
6fb0ead
·
verified ·
1 Parent(s): 2dbe1bf

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -18,11 +18,13 @@ library_name: diffusers
18
 
19
  This repository contains Nunchaku-quantized (SVDQ) versions of [CenKreChro](https://civitai.com/models/1836040/cenkrechro), a text-to-image model based on Chroma and Flux Krea merged by [TiwazM](https://civitai.com/user/TiwazM)
20
 
21
-
22
  Model Files
23
  - [svdq-int4_r32-CenKreChro.safetensors](https://huggingface.co/spooknik/CenKreChro-SVDQ/blob/main/svdq-int4_r32-CenKreChro.safetensors): SVDQuant INT4 (rank 32) CenKreChro model. For users with non-Blackwell GPUs (pre-50-series).
24
  - svdq-int4_r32-qwen-image.safetensors: SVDQuant NVFP4 (rank 32) CenKreChro model. For users with Blackwell GPUs (50-series).
25
 
 
 
 
26
  ### Quality Evaluation
27
 
28
  Below is the quality and similarity evaluated with 256 samples from MJHQ-30K dataset. 256 is a very low sample size, but was done to increase the workflow speed.
 
18
 
19
  This repository contains Nunchaku-quantized (SVDQ) versions of [CenKreChro](https://civitai.com/models/1836040/cenkrechro), a text-to-image model based on Chroma and Flux Krea merged by [TiwazM](https://civitai.com/user/TiwazM)
20
 
 
21
  Model Files
22
  - [svdq-int4_r32-CenKreChro.safetensors](https://huggingface.co/spooknik/CenKreChro-SVDQ/blob/main/svdq-int4_r32-CenKreChro.safetensors): SVDQuant INT4 (rank 32) CenKreChro model. For users with non-Blackwell GPUs (pre-50-series).
23
  - svdq-int4_r32-qwen-image.safetensors: SVDQuant NVFP4 (rank 32) CenKreChro model. For users with Blackwell GPUs (50-series).
24
 
25
+ If you find my models useful please consider: <a href='https://ko-fi.com/B0B21MPRDT' target='_blank'><img height='36' style='border:0px;height:36px;' src='https://storage.ko-fi.com/cdn/kofi6.png?v=6' border='0' alt='Buy Me a Coffee at ko-fi.com' /></a>
26
+
27
+
28
  ### Quality Evaluation
29
 
30
  Below is the quality and similarity evaluated with 256 samples from MJHQ-30K dataset. 256 is a very low sample size, but was done to increase the workflow speed.