[ Accelerator LoRAs ] Applicable to QW21 | Minimax H3 | HYVideo TURBO/LIGHTNING/DMD/FAST - lightx2v / Minimax-h3 1.0

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

Improve the visual details and overall quality of FL2V Turbo.
Develop distillation based on Ref2V.

Preview

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

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

Download (Beta) View on CivitAI

Details

Downloads

11,800

Platform

CivitAI

Platform Status

Available

Created

8/9/2026

Updated

9/26/2026

Deleted

Files

minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors

Size:

1.82 GB

SHA256:

2339acdf19bfe123f46b971ea35d367a84adb85de43627e1eceafa5a5b2b111e

Mirrors

HuggingFace (14 mirrors)

minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors

minimax_h3_lightx2v_turbo_8step_v1.0.safetensors

minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors

minimax_h3_lightx2v_turbo_8step_v1.0.safetensors

minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors

CivitAI (3 mirrors)

minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors

minimaxH3Remix_bf16V06_3140963.safetensors

minimax_h3_fl2v_lightx2v_turbo_4step_v1.0_768p_resized_avg_rank_31_bf16.safetensors

Size:

420.45 MB

SHA256:

9515eee9f642aa0e7fcc401f56d408ef2d6388f81881fe50bddded8220870a4d

Mirrors

HuggingFace (3 mirrors)

minimax_h3_fl2v_lightx2v_turbo_4step_v1.0_768p_resized_avg_rank_31_bf16.safetensors

CivitAI (1 mirrors)

minimax_h3_fl2v_lightx2v_turbo_4step_v1.0_768p_resized_avg_rank_31_bf16.safetensors

minimax_h3_fl2v_turbo_4step_v1.0_768p_comfyui_bf16.safetensors

Size:

1.82 GB

SHA256:

c396a9a06f58399e9df9754b18299818d84a2ddd371724ba48fe4a41221437dc