MiniMax H3: Text to Image
Generate a single still image from a text prompt with MiniMax H3, an omni-modal video model used here for its first-frame decode. No file inputs required: the graph samples an empty latent and decodes it through the H3 video VAE. Best suited to a single subject with a defined light source and a simple or blurred background.
Minimum ComfyUI version: 0.30.0
Models and weights
- minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors ·
models/loras/ - minimax_h3_fl2va_pruned_int8_convrot.safetensors ·
models/diffusion_models/ - minimax_h3_video_vae_fp16.safetensors ·
models/vae/ - qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors ·
models/text_encoders/
ComfyUI nodes
- Basic Guider
- BasicScheduler
- CLIPLoader
- CLIPTextEncode
- EmptyLatentImage
- If/Else Switch
- KSamplerSelect
- LoraLoaderModelOnly
- Model Attention Backend
- RandomNoise
- Resolution Selector
- SamplerCustomAdvanced
- SaveImage
- Separate AV Latent
- UNETLoader
- VAEDecode
- VAELoader
ORIGINAL REPOSITORY
Comfy-Org/workflow_templates ↗GitHub activity
- Stars
- 1,445
- Forks
- 270
- Open issues and PRs
- 98
- Repository size
- ~4,915,364 KB
- Default branch
- main
- Created
- Feb 28, 2025
- Repository updated
- Nov 5, 2026
- Last push
- Nov 5, 2026
- Language
- TypeScript
- License
- MIT
Repository-wide figures from GitHub, checked Nov 5, 2026. Stars are endorsements, not a Mega AI Hub quality rating. Repository size is GitHub’s estimate; a ZIP download may differ.
Resource information
- Deployment
- Local
- Publisher
- Comfy Org
- License
- MIT
- Last record update
- Nov 5, 2026