calcuis
/

ltxv-gguf

@@ -71,7 +71,7 @@ widget:
 - `q2_k` gguf is super fast but not usable; keep it for testing only
 - `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
 - by the way, `0.9_fp8_e4m3fn` and `0.9-vae_fp8_e4m3fn` are working pretty good
-- mix-and-match possible; you could mix up using the vae(s) available with different model file(s) here
 - **gguf-node** is available (see details [here](https://github.com/calcuis/gguf)) for running the new features (the point below might not relate to the model)
 - you are able to make your own `fp8_e4m3fn` scaled safetensors and/or convert it to **gguf** with the new node via comfyui

 - `q2_k` gguf is super fast but not usable; keep it for testing only
 - `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
 - by the way, `0.9_fp8_e4m3fn` and `0.9-vae_fp8_e4m3fn` are working pretty good
+- mix-and-match possible; you could mix up using the vae(s) available with different model file(s) here; test which combination works better
 - **gguf-node** is available (see details [here](https://github.com/calcuis/gguf)) for running the new features (the point below might not relate to the model)
 - you are able to make your own `fp8_e4m3fn` scaled safetensors and/or convert it to **gguf** with the new node via comfyui