Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
Initial release. Drop a folder of images, press Queue per image — ImageIterator batches, QwenVL auto-captions motion and audio per frame, MiniMax H3 (8-step turbo LoRA) animates with native stereo audio. Optimized...
Runtime profile
Source description
Initial release. Drop a folder of images, press Queue per image — ImageIterator batches, QwenVL auto-captions motion and audio per frame, MiniMax H3 (8-step turbo LoRA) animates with native stereo audio. Optimized for 16 GB VRAM (int8_convrot quant). Audio captioning specifically tuned (hard word cap plus literal sound-list format) to avoid garbled or narration-style audio — see USER_GUIDE for detail.
Estimated VRAM requirement
Estimate unavailable
19.5 GB across 1 of 5 model files. Model file total + 25% loading overhead + 2 GB execution buffer, rounded up.
Requirements
6 requirementsSources
1 sourceSource excerpts
1 excerptSource context: 910 downloads · Type Workflows · Base model MiniMax H3
minimax_h3_audio_vae_fp32.safetensors
File unverifiedVAE · SAFETENSORS · Unknown
Checkpoint · 19.5 GB · Hugging Face · Abiray/Minimax-H3-nvfp4-INT4-INT8-Convrot
minimax_h3_turbo_4step_ckpt500_pruned_comfyui.safetensors
Not resolvedLoRA · Unknown
minimax_h3_video_vae_fp16.safetensors
File unverifiedVAE · SAFETENSORS · Unknown
qwen3vl_32b_minimax_h3_int4_convrot.safetensors
Not resolvedText encoder · Unknown
ComfyUI-QwenVL
PossibleNode pack · Registry
