Free ComfyUI workflow for MiniMax H3 text-to-video with built-in audio. Type a prompt and get AI video of your AI influencer, character or cartoon scene.
MiniMax H3Text → Video, AudioBeginner
MiniMax H3 is an open AI video model that generates video with sound in one pass: voices, sound effects and ambience come out already synced to the picture. Describe a scene and this workflow turns it into a short clip, ready to post.
Great for:
AI influencer clips and talking-head videos
Cartoon and animated shorts
Social media video ideas you can test fast
How it works
Write what should happen in the scene, including any dialogue or sound.
Pick a size (vertical 9:16 by default, perfect for Reels and TikTok).
Run it and get a video with audio.
Make it yours with LoRAs
This workflow supports LoRAs. Grab character, style, anime or cartoon LoRAs from CivitAI or Hugging Face, drop them into the LoRA loader, and keep your AI character looking the same in every shot.
Recommended settings6
GPU
H100
H200
RTX PRO 6000
RTX 5090
Sampler
euler
res_multistep
Scheduler
simple
Turbo LoRA
LightX2V 8-step turbo LoRA
Steps
8 with the turbo LoRA at full strength
10-12 with the turbo LoRA at lower strength for better quality
Hugging Face