MiniMax H3 text to video · Auto Prompt + upscale
Turn a scene idea into video with assisted prompting and latent upscaling.
All workflows
Workflow preview
79 KB · JSON file
Need a hand? Load your workflow or troubleshoot your Runpod setup.
- Replace prompt placeholders and supply your own input images, video or audio before running.
- Add your OpenRouter API key to use Auto Prompt.
Models to download
Check the required model files before running this workflow.
- minimax_h3_audio_vae_fp32.safetensors (ComfyUI/models/vae)Model source for minimax_h3_audio_vae_fp32.safetensors (ComfyUI/models/vae)
- minimax_h3_fl2v_turbo_8step_v1.0_768p_comfyui_bf16.safetensors (ComfyUI/models/loras)Model source for minimax_h3_fl2v_turbo_8step_v1.0_768p_comfyui_bf16.safetensors (ComfyUI/models/loras)
- minimax_h3_fl2va_bf16.safetensors (ComfyUI/models/diffusion_models)Model source for minimax_h3_fl2va_bf16.safetensors (ComfyUI/models/diffusion_models)
- minimax_h3_latent_upscaler_3d_fp16.safetensors (ComfyUI/models/latent_upscale_models)Model source for minimax_h3_latent_upscaler_3d_fp16.safetensors (ComfyUI/models/latent_upscale_models)
- minimax_h3_video_vae_fp16.safetensors (ComfyUI/models/vae)Model source for minimax_h3_video_vae_fp16.safetensors (ComfyUI/models/vae)
- qwen3vl_32b_minimax_h3_int8_convrot.safetensors (ComfyUI/models/text_encoders)Model source for qwen3vl_32b_minimax_h3_int8_convrot.safetensors (ComfyUI/models/text_encoders)
- taeh3.safetensors (ComfyUI/models/vae_approx)Model source for taeh3.safetensors (ComfyUI/models/vae_approx)