A workflow uses the latest Open Source MiniMax H3 to generate videos from multiple references.
Other model details are within the workflow.
Try the workflow online(Faster):
Basic:
https://www.runninghub.ai/post/2084116916972908545
Dual Sampler:
https://www.runninghub.ai/post/2086790597210746881
Latent Upscaler:
https://www.runninghub.ai/post/2089678677750923266
Please check the video tutorial before you use this workflow:
Basic: https://rumble.com/v7dotpw-seedance-is-dead-minimax-h3-rebornfree-open-source.html
Dual Sampler: https://rumble.com/v7e3llc-free-open-source-gods-i-make-the-minimax-h3-recreate-a-classic-60-second-sh.html
Latent Upscaler+Local Prompt: https://rumble.com/v7een90-minimax-h3-latent-upscaler-local-prompt-skill-nodeqwen3.8-gguf.html
Custom Nodes Used In Workflow:
Custom Nodes:
https://github.com/T8mars/comfyui-minimax-h3-audio-T8
https://github.com/ptmaster/ComfyUI-PT_H3ConcatAVLatent
https://github.com/WhatDreamsCost/WhatDreamsCost-ComfyUI
https://github.com/smthemex/ComfyUI_UniBlockSwap
https://github.com/chflame163/ComfyUI_Qwen_H3_Prompt
https://github.com/LBH-123-AI/Comfyui_Minimax_h3_latent_Upscaler
Skill:
https://github.com/landon2022/minimax-h3-video-prompt
Description
FAQ
Comments (4)
Just skip it if you want to run something locally. Manager can't find all the custom nodes, and they aren't listed here. Also the tutorial video is in Chinese.
Sorry about this; I forgot to add the tutorial to the description. Now you can check the tutorial for custom node links
https://rumble.com/v7e3llc-free-open-source-gods-i-make-the-minimax-h3-recreate-a-classic-60-second-sh.html
qwen3vl_32b_minimax_h3_int8_convrot.safetensors ????
whats wrong with it? I am using it the whole time. You can find it on hugging face. You can also use an 4b/8b variant with the clipproj-loader from the "ClipProj" pack, you need e.g. a qwen3vl 8b and a mmh3 8b. Or the 4b variant. It works fine.