Sign In
homemodelsimagesvideos3D Modelsarticlescomicsbountieschallengesupdatesshop

Hunyuan Video (Safetensors) - New Uncensored Llama

Updated: Apr 11, 2025

base modelvideohunyuantencent

Download

1 variant available

fp32 SafeTensor

llava-llama-3-8b-text-encoder-tokenizer_FP32.safetensors

Full precision, largest file (pruned) • 29.92 GB

Verified:

Type
Checkpoint Trained
Stats

7,698

Reviews

(383)

Published

Apr 11, 2025

Base Model

Hunyuan Video

Training
Steps: 100,000,000
Epochs: 100,000
Hash
AutoV2
602115CFDD
default creator card background decoration
Reactions - 62291

62.3K

Downloads - 580309

580.3K

Generations - 4872784

4.9M

SDXL Training Contest Participant

License:

Tencent Hunyuan Community License Agreement

Tencent Hunyuan is licensed under the Tencent Hunyuan Community License Agreement, Copyright © 2024 Tencent. All Rights Reserved. The trademark rights of “Tencent Hunyuan” are owned by Tencent or its affiliate.

Powered by Tencent Hunyuan

246d1145-ba3e-4d8e-9a66-30d200fd8b97_1600x1176.png

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.