CivArchive
    Preview 44348533

    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.

    Description

    FAQ

    Comments (37)

    frosty639Apr 28, 2025· 6 reactions
    CivitAI

    So are the diffusion models linked here 'uncensored' or the same as the default ones from tencent and kijai? Which I thought were already uncensored... So why link them in this if it's just an uncensored clip model? I'm confused.

    Felldude
    Author
    Apr 28, 2025

    The TE is a LLM that guides the model, Hunyuan used a unique version of Llava LLama only available in FP16, this model used training from intel that was not directly compatible as a drop in to train the FP32 - The uncensored tag via the LLM was it seemed to guide better results for my prompting style

    frosty639Apr 29, 2025

    @Felldude ok.. so there's no need to change the standard difussion models to the ones you're linking here? just the text encoder?

    Felldude
    Author
    Apr 29, 2025· 2 reactions

    @frosty639 The diffusion model has no change other then conversion to Safetensors

    suede2031691May 1, 2025· 2 reactions
    CivitAI

    So how can I convert Uncensored_Llama_TE_BF16 to fp8_scaled available to comfyui?

    Felldude
    Author
    May 1, 2025

    Well I would use the FP32 to quantize to FP8

    suede2031691May 1, 2025

    @Felldude Thanks, comfy.org will convert to fp8 e4m3 with “multiply the weight be 448 and then store the value (1/448) for unscaling it during inference in the checkpoint”, since I don't know python well, the conversion on my own is always unsuccessful and vram is not sufficient ......

    BigSad11May 2, 2025· 51 reactions
    CivitAI

    Hey everyone! There is a lot of confusion around this checkpoint so I thought I'd make a quick guide to help everyone NOT have the experience I had yesterday when trying to learn this model for the first time. To start off with Uncensored_Llama_TE is NOT a checkpoint. I know. It's confusing... Here's a quick guide to help you know what to download assuming you're already familiar with the workflow.

    Your workflow is going to have:
    Load Diffusion Model.
    Dual Clip Loader.
    Vae.

    All these files are here.
    The Uncensored_Llama versions are actually one of the 2 Clips you need to load!!!! Hope this clarifies any confusion.

    Use the models at the top in this order based on your system.

    -Load Diffusion Model: Comfy 16 or 8 (most likely 8)

    - Dual Clip Loader:
    1.One of the Vision_Clip-L models based on your system
    2. Uncensored_Llama_TE (I know! This is where it goes. The dev recommends 32 if your system can handle it. Read his Full Guide in comments)

    - VAE: We all know VAE by now. Pick one.

    The Kijai models on the far right are for non-native, requiring special nodes.

    Hope this helps you better understand the list up top and what to pick! Clarifying any confusion for new comers! Even though they all show up under "checkpoints", they're not all checkpoint files. Only the Comfy files are the checkpoints. Have fun!

    1969nobodyreallyMay 3, 2025· 1 reaction

    wow.. that got out of hand fast!. Brick killed a guy.. TY!

    henk717gMay 4, 2025

    Is there a way to convert this to huggingface differs format so it can be used in framepack? The original text-ncoder model isn't in this single safetensors format and I haven't gotten this to load at all.

    Felldude
    Author
    May 5, 2025

    @henk717g I have not used framepack but if it has Llava Llama config defined it should be able to use the safetensors files. If it is relying on the config from hugging face you could modify the script to point to the config on huggingface but load the safetensors file localy

    henk717gMay 5, 2025

    @Felldude My one has an offline copy of hunyuanvideo-community/HunyuanVideo at main
    I have tried naming it model.safetensors but for some reason I can't get it to load if I place it in the text_encoder folder instead of the files already there.

    Update: Figured it out. I had to use this conversion script:
    ```
    from safetensors.torch import load_file from transformers import LlamaModel, LlamaConfig import torch # Load the safetensors file file_path = "hunyuanVideoSafetensors_uncensoredLlamaTE.safetensors" state_dict = load_file(file_path) # Initialize the LlamaModel configuration config = LlamaConfig.from_pretrained("text_encoder_") # Create the model and load the weights model = LlamaModel(config) model.load_state_dict(state_dict, strict=False) # Allow partial loading if necessary model.to(dtype=torch.float16) # Save the model in Hugging Face format save_path = "text_encoder" model.save_pretrained(save_path) print(f"Model exported successfully to {save_path}")
    ```

    DPCharlieMay 6, 2025

    is it even worth it ? it seems as if this is alot of work for nothing

    ginxMay 9, 2025· 1 reaction

    yea made it work but i dont see any difference, is it better for more complex prompts? there is no real example of what it really accomplishes.

    3cchi33v33Jun 29, 2025· 1 reaction

    Do you know if this works with image to video?

    FamilyFriendlyMay 11, 2025· 3 reactions
    CivitAI

    Really good stuff

    fcmpMay 17, 2025· 8 reactions
    CivitAI

    if you get this error:
    Missing Node Type

    HunyuanVideoLoaderLora
    type this in manager to find the custom node:
    ComfyUI-HunyuanVideoMultiLora

    wasn't showing up in the Missing folder for me

    Dead_Internet_TheoryJun 18, 2025· 4 reactions
    CivitAI

    Can this be used with FramePack? e.g., FramePack Studio (one of the UIs for it)

    Felldude
    Author
    Jun 18, 2025

    If it allows for local loading of the LLM

    caipes1981135Jul 2, 2025

    NO

    caipes1981135Jul 2, 2025· 3 reactions

    @Felldude FRAMEPACK OR FRAMEPACK STUDIO, does not allow any custom models it fetches everything with custom json structures

    foggy1dayMar 22, 2026

    @caipes1981135 This person is just spreading bad information!

    rgtailsJun 23, 2025· 3 reactions
    CivitAI

    Guide give 404

    Felldude
    Author
    Jun 23, 2025

    Does it say civitai.com or .green - Green will give a 404

    rgtailsJun 23, 2025

    ^^ normal version work thx

    3cchi33v33Jun 29, 2025· 9 reactions
    CivitAI

    Does this work with Image to Video?

    pepito12ewq274Sep 4, 2025

    yo tambien lo estoy buscado el image to video :(

    eric0524Jul 1, 2025· 6 reactions
    CivitAI

    Has anybody figured out where these trained checkpoint files go in the wan2GP file structure?

    lilmonsterb69Jul 12, 2025

    I have the same question, I just finished installing Wan2GP locally and not even on their md files I see anything for this. All I could find was only for ComfyUI which I don't want to use

    ZehlhiannOct 24, 2025· 1 reaction

    You got two directories for Lora with Wan2GP :

    loras_hunyuan/ - Hunyuan Video text2video loras

    loras_hunyuan_i2v/ - Hunyuan Video image2video loras

    pure2103Jul 13, 2025· 4 reactions
    CivitAI

    Please provide more than 1 lora method. in this workflow please

    DPCharlieJul 28, 2025

    right click clone lora loader

    lighthorsexajz830Aug 31, 2025· 4 reactions
    CivitAI

    Hello it is possible to set up this model in frampack studio f1 which works with hunyuan video thanks for your help ;)

    colinuSep 5, 2025

    Since it's not a framepack model unfortunately it's not possible.

    @colinuOK I take note thank you for your answer

    lifeonthelimb207Mar 8, 2026

    Wrong. the newest FPS will convert and run ANY Hunyuan Video lora!

    unknowncheatssleeve022521Apr 16, 2026
    CivitAI

    HI , does this work for like motion Control reference nsfw ? so i upload an image near to my nsfw Motion control , and run this with that to then generate a nsfw video ? based on the motion control?

    Checkpoint
    Hunyuan Video

    Details

    Downloads
    464
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    4/24/2025
    Updated
    5/15/2026
    Deleted
    5/6/2025

    Files

    hunyuanVideoSafetensors_llavaLlamaTE.safetensors