CivArchive
    Accelerator LoRAs - lightx2v / Minimax-h3 1.0
    NSFW

    Metafilm`s CATEGORICALINDEX 》

    Grouped by base model, bases ordered by first production use (newest first); brands inside each base ordered by heat (total downloads); works inside each brand newest first. 282 works across 21 base models.

    Type tags: fine-tune / LoRA / 工作流 / ControlNet. Data collected 2026-10-23.

    ▍RedCraft 红潮 ⌝ ▍Dark Beast 黑兽 ⌝ ▍FineView 欢视 ⌝ 
    ▍GGUF/BF16 for Local Multimodal ENV

    Drama Story2 on Krea 2 Turbo https://civarchive.com/models/452459/?modelVersionId=3393223 GGUF Q8
    REDGPT for realistic drama stills https://civarchive.com/models/452459/?modelVersionId=3131246 GGUF Q8
    Krea 2 mix from the 赤佬3 https://civarchive.com/models/958009/?modelVersionId=3139241 Q4KM
    K2T BUZZDEAL build for commercial https://civarchive.com/models/958009/?modelVersionId=3331574 Q4KM
    REDQW21 Turbo texture-fixed https://civarchive.com/models/3003597 BF16
    REF2i Hyper photographic https://civarchive.com/models/3015888 BF16
    K2T for colorful youth https://civarchive.com/models/2242173/?modelVersionId=3365025 Q4KM
    FLUX.1 Fill inpainting https://civarchive.com/models/958009/?modelVersionId=1445047 Q4KM
    De-distilled Flux.1 with Aesthetic https://civarchive.com/models/958009/?modelVersionId=1387169 Q4KM
    Krea 2 hardcore Dark Beast 3 edition https://civarchive.com/models/2242173/?modelVersionId=3173268 BF16
    ZImage Turbo hardcore https://civarchive.com/models/2242173/?modelVersionId=2699886 FP32/BF16
    SDXL 1.0 entry in the Dark Beast https://civarchive.com/models/2242173/?modelVersionId=2712294 FP32/BF16
    Retro SD 1.5 HD rebuild https://civarchive.com/models/958009/?modelVersionId=1298797 FP32/BF16
    OpenMOSS MOSS-Image https://civarchive.com/models/3007993/?modelVersionId=3436921 BF16
    MOSS 4 fêtesnap NSFH https://civarchive.com/models/3007993/?modelVersionId=3448658 BF16
    Paid MiniMax H3 director package https://civarchive.com/models/1295569/?modelVersionId=3375757 BF16

    做好工具人 服务艺术家

    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 截止 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.

    预览

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

    Apache-2.0 license

    Description

    Minimax-H3-Turbo by LightX2V

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

    Note

    v0.1 is a preview release. 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

    FAQ

    Comments (6)

    laogetmd862Aug 9, 2026
    CivitAI

    牛逼啊，我经常刷到你做的视频

    mankogamerhnAug 9, 2026
    CivitAI

    I have a question, does this lora works with reference to video or only first and last frame video? If I have a turbo lora activated will it crash or will work together?

    ArttTakuAug 9, 2026
    CivitAI

    Heck yeah, 8 steps makes much more sense, 4 steps was just pushing the model way too hard.

    hatt2Aug 10, 2026

    i think this is 4 step ?

    ArttTakuAug 10, 2026

    @hatt2 Yeah, but it can also be used with 8 steps, not sure if the other ones allowed this too.

    insanelime1012rk321Aug 10, 2026
    CivitAI

    very thx ,,4 sec of vid now i can generate in 4 min owesome

    LORA
    MiniMax H3
    by AiMeASOP
    Download (Beta) View on CivitAI
    t2v
    tool
    hunyuanvideo
    video

    Details

    Downloads
    13,689
    Platform
    CivitAI
    Platform Status
    Available
    Created
    8/9/2026
    Updated
    11/11/2026
    Deleted
    -

    Files

    minimax_h3_fl2v_lightx2v_turbo_8step_v1.0_resized_avg_rank_24_bf16.safetensors

    Size:
    347.75 MB
    SHA256:
    8e05b7b982c3aff7deb692a188c8a8d8acaeff8a12abfe1aeac822fb8ee3f0b7

    Mirrors

    HuggingFace (15 mirrors)
    CivitAI (1 mirrors)

    minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors

    Size:
    1.82 GB
    SHA256:
    2339acdf19bfe123f46b971ea35d367a84adb85de43627e1eceafa5a5b2b111e

    Mirrors

    HuggingFace (26 mirrors)
    CivitAI (3 mirrors)
    ModelScope CN (1 mirrors)

    minimax_h3_fl2v_lightx2v_turbo_4step_v1.0_768p_resized_avg_rank_31_bf16.safetensors

    Size:
    420.45 MB
    SHA256:
    9515eee9f642aa0e7fcc401f56d408ef2d6388f81881fe50bddded8220870a4d

    Mirrors

    HuggingFace (4 mirrors)
    CivitAI (1 mirrors)

    minimax_h3_fl2v_lightx2v_turbo_4step_v0.1_comfy_resized_avg_rank_21_bf16.safetensors

    Size:
    300.29 MB
    SHA256:
    3a069f26fbc33f377a60dc72dd9e15f2aa42aa1d1b44915fded835716672dd36

    Mirrors

    HuggingFace (8 mirrors)
    CivitAI (4 mirrors)

    minimax_h3_fl2v_turbo_4step_v1.0_768p_comfyui_bf16.safetensors

    Size:
    1.82 GB
    SHA256:
    c396a9a06f58399e9df9754b18299818d84a2ddd371724ba48fe4a41221437dc

    Mirrors

    HuggingFace (12 mirrors)
    CivitAI (2 mirrors)
    ModelScope CN (1 mirrors)

    minimax_h3_ref2v_lightx2v_turbo_4step_v0.1_resized_avg_rank_20_bf16.safetensors

    Size:
    292.52 MB
    SHA256:
    9ea3bd3a6aac22994153e294cf1ecab0a8766fc0f8d056ace645a01d1a6a4daf

    Mirrors

    HuggingFace (2 mirrors)
    CivitAI (1 mirrors)

    minimax_h3_fl2v_turbo_4step_v0.1_768p_sla_comfyui_bf16.safetensors

    Size:
    1.82 GB
    SHA256:
    5cae6df40a06ea825f85fc8876c9ea1c9692c833a9af07bb8b3bac9ce2a71bac

    Mirrors

    HuggingFace (3 mirrors)
    CivitAI (1 mirrors)