Sign In
homemodelsimagesvideospostsarticlesbountieschallengeseventsupdatesshop

Hunyuan Video (Safetensors) - New Uncensored Llama

3.2k

83.6k

2k

Updated: Apr 11, 2025

base modelvideohunyuantencent

Download (815.68 MB)

Verified:

SafeTensor

Type

Checkpoint Trained

Stats

2,938

0

Reviews

(42)

Published

Feb 1, 2025

Base Model

Other

Training

Steps: 1,111,111
Epochs: 100,000

Hash

AutoV2
4A0BBAB8EF
SDXL Training Contest Participant
Felldude's Avatar

Felldude

License:

Hunyuan Video

Kijai marked files only for use with Kijai Nodes You do not need them for Comfy Native

  • Full Guide to picking the correct file above

  • Workflow for 8GB Card users

  • Uncensored llama will work with COMFY Native

Using the Kajai marked models on COMFY native will cause rainbow or black output.

I do not recommend the the FP8 VAE unless you are trying to fit all models into GPU, see the guide for 4090 full GPU launch commands.

Technical details regarding "Uncensored"

The model used for Hunyuan was based on llava-llama-3 8 billion parameter LLM. The Intel vision tuned model was used to refine the tokenized model restoring over 5 million values.