Hugging Face's logo

rzgar
/
LTX-2.3-Cinematic-VAE

Image-Text-to-Video
Diffusers
image-to-video
text-to-video
video-to-video
audio-to-video
text-to-audio
video-to-audio
audio-to-audio
text-to-audio-video
image-to-audio-video
image-text-to-audio-video
ltx-2
ltx-2-3
ltx-video
ltxv
lightricks
Model card Files
xet
 Community
1

A custom VAE for LTX-Video 2.3 that bakes a cinematic color grade directly into the decoder. It applies a subtle, darker greenish-teal tint to the output, evoking a soft, cinematic "The Matrix" like aesthetic. Because the color grade is baked into the VAE weights, it eliminates the need for post-processing color correction, giving you the final cinematic look straight out of generation.

Left: Default | Right: This VAE

Files

File Direct Link
LTX23_video_vae_bf16_cinematic.safetensors Download

Usage

  • Simply save the VAE in ComfyUI models/vae folder.
  • If you’re using monolithic checkpoints, use the KJ VAE Loader.
Downloads last month
1,382
Inference Providers NEW
Image-Text-to-Video
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for rzgar/LTX-2.3-Cinematic-VAE

Base model

Lightricks/LTX-2.3
Finetuned
(101)
this model

Space using rzgar/LTX-2.3-Cinematic-VAE 1