Downloads · 30 days
3.4K
45% of all-time downloads
Rkss/Minimax_h3_fl2v_lightx2v_turbo_4to8step_768p_v4_step600_dareties_native
Minimax_h3_fl2v_lightx2v_turbo_4to8step_768p_v4_step600_dareties_native is a machine learning model from Rkss. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for minimax-h3.
Experimental native-pruned version of SilverOxides' MiniMax H3 Turbo LoRA for ComfyUI.
Downloads · 30 days
3.4K
45% of all-time downloads
All-time downloads
7.5K
Public
Repo size
4.9 GB
Likes
2
Public
Click a slice to open those files.
.safetensors3.3 GB · 100%
From the Hugging Face model README
Experimental native-pruned version of SilverOxides' MiniMax H3 Turbo LoRA for ComfyUI.
Minimax_h3_fl2v_lightx2v_turbo_4to8step_v0.1-v1.0_768p_v4_step600_dareties_fro095
Load with ComfyUI's LoRA loader node.
Two versions. Pruned Adaln modules and a ported one.
This is not mathematically equivalent to the original LoRA
Source: https://huggingface.co/silveroxides/MiniMax-H3_tests/tree/main/experimental
0.80 – 1.11.0 – 1.1Low strength may cause artifacts, softness, or voice instability. Use when you see oversharpen/detailed
High strength may become overcooked. Use when you see blurry ghosting.
Results may vary between workflows.
This is an experimental build.