calcuis commited on
Commit
813ef2f
·
verified ·
1 Parent(s): 0714451

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -6
README.md CHANGED
@@ -35,21 +35,21 @@ widget:
35
  url: samples\hat.webp
36
  ---
37
  # **gguf quantized version of kontext**
38
- - run it with `gguf-connector`; simply execute the command below in console/terminal
 
39
  ```
40
  ggc k0
41
  ```
42
  >
43
  >GGUF file(s) available. Select which one to use:
44
  >
45
- >1. flux-kontext-iq4_nl.gguf
46
- >2. flux-kontext-mxfp4_moe.gguf
47
- >3. flux-kontext-q2_k_s.gguf (good enough for tryout)
48
  >
49
  >Enter your choice (1 to 3): _
50
  >
51
- - opt a `gguf` file in your current directory to interact with; nothing else
52
- - *new 8-step operation with `k0`; save up to 70% loading time
53
 
54
  ## **run it with gguf-node via comfyui**
55
  - drag **kontext** to > `./ComfyUI/models/diffusion_models`
 
35
  url: samples\hat.webp
36
  ---
37
  # **gguf quantized version of kontext**
38
+ - run it straight with `gguf-connector`
39
+ - opt a `gguf` file in the current directory to interact with by:
40
  ```
41
  ggc k0
42
  ```
43
  >
44
  >GGUF file(s) available. Select which one to use:
45
  >
46
+ >1. flux-kontext-lite-q2_k.gguf
47
+ >2. flux-kontext-lite-q4_0.gguf
48
+ >3. flux-kontext-lite-q8_0.gguf
49
  >
50
  >Enter your choice (1 to 3): _
51
  >
52
+ note: try experimental lite model with 8-step operation; save up to 70% loading time
 
53
 
54
  ## **run it with gguf-node via comfyui**
55
  - drag **kontext** to > `./ComfyUI/models/diffusion_models`