liuxin9494/h3-models

H3 deployment model collection

This repository preserves the H3 model files used by the owner's ComfyUI deployment. The models were copied from the owner's RunPod network volume without modifying the originals.

Layout

• unet/: H3 diffusion model
• text_encoders/: H3 Qwen3-VL text encoder
• vae/: video and audio VAEs
• loras/minimaxh3/: H3 LoRA collection
• models-manifest.json: published only after all included files have verified sizes and SHA256 hashes

For reproducible deployment, download the manifest and its listed model files from the same immutable repository commit. Verify every file against the manifest before making it available to ComfyUI. Preserve relative paths under the Pod's local model cache.

The repository is public by the owner's explicit authorization. No access token is required for public downloads. Do not embed upload credentials in inference images.

Licensing

This collection does not grant a new blanket license. Each model and adapter retains its original author's license and usage conditions. Consult the relevant upstream model documentation before redistribution or use.

Validation scope

File integrity verification is not a statement that every optional LoRA has been tested for inference. Runtime acceptance uses a non-explicit, fully clothed adult portrait workflow and the Turbo adapter. Model hosting speed and inference speed are separate measurements.