RunningHub workflow page: https://www.runninghub.ai/zh-cn/post/2084544656423088130?inviteCode=rh-v1111
MiniMax H3 Text-to-video
A MiniMax H3 omni-modal video graph exported from episode 288. 23 nodes / 24 links, one branch. The saved prompt is a 10-second 16:9 3840x2160 first-person MotoGP POV scene. 16:9 at 0.8 MP.
Saved configuration
- UNETLoader
minimax_h3_fl2va_bf16.safetensors; CLIPLoaderqwen3vl_32b_minimax_h3_int8_convrot.safetensors(type minimax); VAELoader videominimax_h3_video_vae_fp16.safetensors+ audiominimax_h3_audio_vae_fp32.safetensors. - The saved graphs contain no LoRA nodes.
- Sampling:
KSamplerSelectres_multistep withBasicSchedulersimple, 20 steps, denoise 1;SamplerCustomAdvancedfor the custom chain. - Conditioning:
MiniMaxH3ImageToVideo/MiniMaxH3ReferenceToVideosaved at 1344x768 / 124 / match where present; ResolutionSelector and duration values are quoted per item above; output goes to SaveVideo prefixvideo/MiniMax_H3.
How to use
No image input at all: the prompt is the only content input. MiniMaxH3ImageToVideo runs as a pure T2V conditioning node.
Limits and not-verified items
No inference was run for this listing: no speed, VRAM, audio-sync or quality claim is made. Values are quoted from the saved nodes. The graph's notes link the official Comfy-Org/MiniMax-H3 model files and the MiniMax blog; those notes are preserved and this listing does not claim to be the original template author. Weights, encoder and VAEs are not bundled; check their licenses separately. The cover image is a promotional still, not a frame produced by this graph.
Tutorial: YouTube · Bilibili. Workflows supplied through AI-KSK; verify workflow, node, model, image/audio and cover rights separately. No blanket commercial or redistribution license is asserted.
Description
RunningHub workflow page: https://www.runninghub.ai/zh-cn/post/2084544656423088130?inviteCode=rh-v1111
MiniMax H3 Text-to-videoA MiniMax H3 omni-modal video graph exported from episode 288. 23 nodes / 24 links, one branch. The saved prompt is a 10-second 16:9 3840x2160 first-person MotoGP POV scene. 16:9 at 0.8 MP.
Saved configuration- UNETLoader
minimax_h3_fl2va_bf16.safetensors; CLIPLoaderqwen3vl_32b_minimax_h3_int8_convrot.safetensors(type minimax); VAELoader videominimax_h3_video_vae_fp16.safetensors+ audiominimax_h3_audio_vae_fp32.safetensors. - The saved graphs contain no LoRA nodes.
- Sampling:
KSamplerSelectres_multistep withBasicSchedulersimple, 20 steps, denoise 1;SamplerCustomAdvancedfor the custom chain. - Conditioning:
MiniMaxH3ImageToVideo/MiniMaxH3ReferenceToVideosaved at 1344x768 / 124 / match where present; ResolutionSelector and duration values are quoted per item above; output goes to SaveVideo prefixvideo/MiniMax_H3.
No image input at all: the prompt is the only content input. MiniMaxH3ImageToVideo runs as a pure T2V conditioning node.
Limits and not-verified itemsNo inference was run for this listing: no speed, VRAM, audio-sync or quality claim is made. Values are quoted from the saved nodes. The graph's notes link the official Comfy-Org/MiniMax-H3 model files and the MiniMax blog; those notes are preserved and this listing does not claim to be the original template author. Weights, encoder and VAEs are not bundled; check their licenses separately. The cover image is a promotional still, not a frame produced by this graph.
Tutorial: YouTube · Bilibili. Workflows supplied through AI-KSK; verify workflow, node, model, image/audio and cover rights separately. No blanket commercial or redistribution license is asserted.