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
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("rzgar/LTX-2.3-Cinematic-VAE", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]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/vaefolder. - If you’re using monolithic checkpoints, use the KJ VAE Loader.
- Downloads last month
- 1,013
Model tree for rzgar/LTX-2.3-Cinematic-VAE
Base model
Lightricks/LTX-2.3