import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("stdstu123/LynnReal-Onmi-light-vae", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]LynnReal Lightweight Video VAE
Code: LynnReal-AI/LynnReal-Omni
🆕 Latest updates
- 2026-09-18 · ComfyUI node pack fix — the Flash workflows no longer stop with
RuntimeError: aimdo memory compile erroron machines where comfy-aimdo's DynamicVRAM is active (a cu13x torch, e.g. an RTX 5090). Updatecomfyui/custom_nodes/ComfyUI-LynnRealand re-run. - 2026-09-17 · Light VAE in ComfyUI — the distilled 26-block decoder now loads through the
LynnRealH3VAELoadernode in the main bundle (272/16 tiles), and is the decoder the Flash three-step workflows use.
Full history: CHANGELOG.md in the main repository.
A complete codec with the unchanged MiniMax H3 encoder and a distilled 26-block video decoder. Latent channels, normalization, spatial scale and temporal compression match the official VAE. Deployment uses the decoder EMA parameters.
config.json and the indexed Safetensors shards follow the Diffusers component
layout. decode_config.json records the release decoder settings. Load with
model.light_vae.LightVAE.from_pretrained("weight/light-vae"), or pass
--light-vae weight/light-vae to script/sample.py. Native decoding tiles are
the default; precision and tile geometry must accompany speed/quality comparisons.
The codec changes reconstruction, not the denoiser latent interface. The same
latent need not decode to identical RGB under the official and lightweight VAE.
See LICENSE and the release NOTICE for MiniMax H3 terms and attribution.
- Downloads last month
- 457