Please check our repository or the LightX2V MiniMax-H3 examples to reproduce the results.
Please check the model specifications for more details.
Try the MiniMax-H3 Turbo LoRA directly in LightX2V Studio:
The Studio currently uses the FL2V 8-step v1.0 768p LoRA, which provides improved video and audio generation quality with 8-step inference.
The model version deployed in the Studio may be updated over time.
Integrate MiniMax-H3 Turbo into your application through the LightX2V API:
minimax_h3_fl2v_turbo_4step_v1.1_768p_fp8.safetensors 34 GBminimax_h3_fl2v_turbo_4step_v1.2_768p_comfyui_bf16.safetensors 2.0 GBminimax_h3_fl2v_turbo_8step_v1.0_768p_comfyui_bf16.safetensors 2.0 GBminimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors 2.0 GBminimax_h3_ref2v_turbo_4step_v0.1_comfyui_bf16.safetensors 2.0 GBminimax_h3_ref2v_turbo_8step_v1.0_768p_comfyui_bf16.safetensors 2.0 GBminimax_h3_fl2v_turbo_4step_v1.0_768p_comfyui_bf16.safetensors 2.0 GBminimax_h3_fl2v_turbo_4step_v1.1_768p_comfyui_bf16.safetensors 2.0 GBminimax_h3_fl2v_turbo_4step_v0.1.safetensors 1.4 GBminimax_h3_fl2v_turbo_4step_v1.0_768p_bf16.safetensors 1.4 GBminimax_h3_fl2v_turbo_4step_v1.1_768p_bf16.safetensors 1.4 GBminimax_h3_fl2v_turbo_4step_v1.2_768p_bf16.safetensors 1.4 GBminimax_h3_fl2v_turbo_8step_v1.0_768p_bf16.safetensors 1.4 GBminimax_h3_ref2v_turbo_8step_v1.0_768p_bf16.safetensors 1.4 GBminimax_h3_fl2v_turbo_8step_v1.0_bf16.safetensors 1.4 GBminimax_h3_ref2v_turbo_4step_v0.1_bf16.safetensors 1.4 GB