Instructions to use Kijai/LTX2.3_comfy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use Kijai/LTX2.3_comfy with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
blurry
#26
by Hairee - opened
all of my generation results are blurry, what do i miss? even use a basic workflow and another workflow, the results still same.
RTX3090 and 64gb of ram
maybe using dev model with low steps and cfg 1, without distilled lora?
Try set the main model to distilled version, or use the dev model + distilled lora (if not aiming to use higher steps and cfg values)
Just using the distilled model is probably the easiest choice though.
(but could be other things, like incompatible combo of gguf models, video vae etc. But hard to guess without more info)
thanks, i will try it