Update README.md
Browse files
README.md
CHANGED
@@ -60,7 +60,7 @@ widget:
|
|
60 |
- drag ltx-video-vae.safetensors ([838MB](https://huggingface.co/calcuis/ltxv-gguf/blob/main/ltx-video-vae.safetensors)) to > ./ComfyUI/models/vae
|
61 |
|
62 |
## **run it straight (no installation needed way)**
|
63 |
-
- run the .bat file in the main directory (assuming you are using the gguf-
|
64 |
- drag the workflow json file (below) to > your browser
|
65 |
|
66 |
### **workflow**
|
@@ -72,7 +72,7 @@ widget:
|
|
72 |
- `0.9.1_fp8_e4m3fn` and `0.9.1-vae_fp8_e4m3fn` are **not working**; but keep them here, see who can figure out how to make them work
|
73 |
- by the way, `0.9_fp8_e4m3fn` and `0.9-vae_fp8_e4m3fn` are working pretty good
|
74 |
- mix-and-match possible; you could mix up using the vae(s) available with different model file(s) here; test which combination works better
|
75 |
-
- **gguf-node** is available (see details [here](https://github.com/calcuis/gguf)) for running the new features (the point below might not directly related to the model)
|
76 |
- you are able to make your own `fp8_e4m3fn` scaled safetensors and/or convert it to **gguf** with the new node via comfyui
|
77 |
|
78 |
### **reference**
|
|
|
60 |
- drag ltx-video-vae.safetensors ([838MB](https://huggingface.co/calcuis/ltxv-gguf/blob/main/ltx-video-vae.safetensors)) to > ./ComfyUI/models/vae
|
61 |
|
62 |
## **run it straight (no installation needed way)**
|
63 |
+
- run the .bat file in the main directory (assuming you are using the gguf-node [pack](https://github.com/calcuis/gguf/releases) below)
|
64 |
- drag the workflow json file (below) to > your browser
|
65 |
|
66 |
### **workflow**
|
|
|
72 |
- `0.9.1_fp8_e4m3fn` and `0.9.1-vae_fp8_e4m3fn` are **not working**; but keep them here, see who can figure out how to make them work
|
73 |
- by the way, `0.9_fp8_e4m3fn` and `0.9-vae_fp8_e4m3fn` are working pretty good
|
74 |
- mix-and-match possible; you could mix up using the vae(s) available with different model file(s) here; test which combination works better
|
75 |
+
- **gguf-node** is available (see details [here](https://github.com/calcuis/gguf)) for running the new features (the point below might not be directly related to the model)
|
76 |
- you are able to make your own `fp8_e4m3fn` scaled safetensors and/or convert it to **gguf** with the new node via comfyui
|
77 |
|
78 |
### **reference**
|