calcuis commited on
Commit
e80ad73
1 Parent(s): cad1707

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -33,11 +33,11 @@ tags:
33
  - example workflow for the original [safetensors](https://github.com/calcuis/comfy/blob/main/workflow-sd3.5m-safetensors.json) 🎃
34
 
35
  ### Bug reports (or brief review)
36
- - t/q1_0 and t/q2_0; doesn't work; encountering np.uint32(34 & 35) invalid GGMLQ type error
37
- - q2_k is super fast; but looks like x-ray film; might be good for medi research or abstract stylist
38
  - q3 family is fast; finger issue can be easily detected but picture quality is interestingly good
39
  - notice the same file size in 0 and s models; still keep them all here; see who can deal with it
40
- - q4 and above should be no problem for general to high quality production overall
41
 
42
  ### Upper tier sets
43
  - sd3.5-[large](https://huggingface.co/calcuis/sd3.5-large-gguf) (recommended)
 
33
  - example workflow for the original [safetensors](https://github.com/calcuis/comfy/blob/main/workflow-sd3.5m-safetensors.json) 🎃
34
 
35
  ### Bug reports (or brief review)
36
+ - t/q1_0 and t/q2_0; doesn't work (invalid GGMLQ type error)
37
+ - q2_k is super fast; but might be good for medical research or abstract stylist
38
  - q3 family is fast; finger issue can be easily detected but picture quality is interestingly good
39
  - notice the same file size in 0 and s models; still keep them all here; see who can deal with it
40
+ - q4 and above should be no problem for general to high quality production
41
 
42
  ### Upper tier sets
43
  - sd3.5-[large](https://huggingface.co/calcuis/sd3.5-large-gguf) (recommended)