CivArchive
    [ Accelerator LoRAs ] Applicable to QW21 | Minimax H3 | HYVideo TURBO/LIGHTNING/DMD/FAST - Llavallama3 FP8+VAE FP16
    NSFW

    QW21-Turbo-0.1 by Viggle

    Steps 4-16 CFG=1 T2i/i2i

    演示图片同时使用了 Viggle/Qwen-Image-2.1-viggle-turbo 和 REDQW21 UNLOCKED LoRA (with NV DLSS_NR)
    仅作为[ 研究或评估 ]用途内使用 / only for the research or evaluation purposes

    The demo images uses both Viggle/Qwen-Image-2.1-viggle-turbo and REDQW21 UNLOCKED LoRA simultaneously
    Built with Qwen, Applicable to Qwen-Image-2.1

    Viggle/Qwen-Image-2.1-viggle-turbo source repo:
    https://huggingface.co/Viggle/Qwen-Image-2.1-viggle-turbo

    All credit belongs to the original model author. License is the same as the original model.

    Model: Viggle/Qwen-Image-2.1-viggle-turbo · Built with Qwen — distilled from Qwen/Qwen-Image-2.1, which is released under the Qwen RESEARCH LICENSE AGREEMENT (non-commercial: research or evaluation purposes only).

    Built with Qwen. A 4-step distilled student of Qwen/Qwen-Image-2.1, trained by Viggle with Distribution Matching Distillation. It does both text-to-image and instruction-driven editing with 1–3 reference images in 4 transformer passes instead of 40, with no classifier-free guidance.

    Two students are shipped — pick one:

    • transformer/ — full fine-tuned transformer (bf16, 14.2 GB). Replaces the base transformer; exact, no adapter. This is what the demo Space runs by default and the one we currently recommend — in our qualitative comparison it edits more faithfully than the LoRA.

    • Qwen-Image-2.1-viggle-turbo-4step-lora-r64.safetensors — LoRA adapter (rank 64, 340 MB) loaded on top of the base transformer at runtime. Smaller download, slightly weaker.

    Status: v0.1 preview, work in progress — this release still falls short of the base model. On complicated image editing (multi-reference composition, face swaps, identity-preserving edits, instructions with several constraints) it is clearly worse than the 40-step base model. Text-to-image at 4 steps is usable. We are still working on it and will update this repository as the distillation improves; treat the current weights as a preview, not a replacement for the base model.

    Minimax-H3-Turbo by LightX2V

    Minimax-H3-Turbo provides batch MiniMax-H3 inference and NFE/LoRA comparisons.

    Repos

    Kijai/MiniMax-H3_comfy Minimax-H3-Turbo ComfyUI v0.1

    lightx2v/Minimax-h3-Turbo Minimax-h3-Turbo Diffusers/ComfyUI v1.0

    Note

    Its current visual quality can be reviewed in the linked examples, and the image details still need improvement. An enhanced version is in development.

    This Edition is compatible with the ComfyUI-pruned

    MiniMax H3 FL2VA model（20B）.

    Roadmap

    1. Improve the visual details and overall quality of FL2V Turbo.

    2. Develop distillation based on Ref2V.

    Preview

    https://huggingface.co/lightx2v/Minimax-h3-Turbo/discussions/2

    Apache-2.0 license

    Description

    hunyuan_video_vae_bf16.safetensors 492.98MB

    llava_llama3_fp8_scaled.safetensors 9.09GB

    clip_l.safetensors 246.14MB

    ---

    Hunyuan Video repackaged for ComfyUI use.

    FAQ

    Comments (11)

    Kung_fu_PronFeb 1, 2025· 1 reaction
    CivitAI

    do i have to use this with a specific hunyuan model? or the 12gb one works fine?

    AiMetatron
    Author
    Mar 5, 2025· 1 reaction

    Sure, 12GB can run

    ThermaMar 9, 2025
    CivitAI

    Could you re-train them for wan1.2 14b and 1.3b please?

    redred3monthMar 11, 2025
    CivitAI

    is this just a lora loader node to import into workflow and it will accelerated ? Is it right?

    IckeBinsMay 8, 2025
    CivitAI

    Did it work in FramePack-Studio?

    Marz1887May 9, 2025

    I tried it but couldnt get it to work

    able2Jun 6, 2025

    It seems to not work with FramePack for now (both in ComfyUI and Framepack Studio). Not pretty sure why but if it works it'll be great.

    lorbJun 22, 2025

    it is OK for framepack-studio v0.4

    bodaidar213May 17, 2026
    CivitAI

    Hi there, this does not work with framepack studio..

    Sasori7Aug 9, 2026· 8 reactions
    CivitAI

    an example workflow would help.

    AiMetatron
    Author
    Aug 9, 2026

    https://civitai.red/models/579280/minimax-h3-krea2-and-ltx23-and-ideogram-4-wf-in-collection

    LORA
    Hunyuan Video
    by AiMetatron
    Download (Beta)
    hunyuanvideo
    t2v
    tool
    video
    nsfw
    hunyuan
    v2v

    Details

    Downloads
    668
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    12/23/2024
    Updated
    8/4/2026
    Deleted
    11/13/2025

    Files

    hunyuan_video_vae_bf16.safetensors

    Size:
    470.15 MB
    SHA256:
    e8f8553275406d84ccf22e7a47601650d8f98bdb8aa9ccfdd6506b57a9701aed

    Mirrors

    HuggingFace (15 mirrors)
    CivitAI (1 mirrors)
    TensorFiles (1 mirrors)
    ModelScope (1 mirrors)

    clip_l.safetensors

    Size:
    234.74 MB
    SHA256:
    660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd

    Mirrors

    HuggingFace (2001 mirrors)
    CivitAI (29 mirrors)
    TensorFiles (1 mirrors)
    CivitasBay (1 mirrors)
    ModelScope (7 mirrors)
    ModelScope CN (6 mirrors)