Model reference · open weights

h3-vbvr

Available as managed deployment Licence fee Video Patarapoom · community Image→video 1 variants 11k dl/mo

h3-vbvr is an open-weight video model from Patarapoom. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

Released byPatarapoom
TypeVideo models
TaskImage→video
Runs withminimax-h3
Released2026-08-18
Popularity11k downloads / month
LicenceCommercial licence needed

About

What h3-vbvr is

Unmodified copies of 6 files (40.77 GB), re-hosted for operational reasons only. Nothing here has been retrained, quantised, converted or edited -- byte-for-byte the upstream blobs, in the ComfyUI category layout.

Why it exists: RunPod Serverless "cached models" pulls a whole repo onto each worker, and the upstream repos hold many variants we never load. Mirroring just the files one render touches is the difference between hundreds of gigabytes per worker and 41 GB.

Read the full model card

Contents

filesizefrom
diffusion_models/minimax_h3_hybrid_fl2va_ref2va_b20-49-int8.safetensors20.97 GBsmhfacct/Minimax-H3-fl2va-ref2va-hybrid-models
text_encoders/qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors15.69 GBComfy-Org/MiniMax-H3
vae/minimax_h3_video_vae_int8_convrot.safetensors3.17 GBKijai/MiniMax-H3-experimental
vae/minimax_h3_audio_vae_fp32.safetensors0.61 GBComfy-Org/MiniMax-H3
loras/minimax_h3_ref2v_lightx2v_turbo_4step_v0.1_resized_avg_rank_20_bf16.safetensors0.31 GBKijai/MiniMax-H3_comfy
loras/VBVR_H3_attn_only.safetensors0.03 GBPatarapoom/H3_lora

Licence

Each file remains under the licence of its upstream repository, linked in the table above -- this mirror grants nothing further and modifies nothing. Check the source repo before any redistribution or commercial use.

No LICENSE.md is shipped here, deliberately. The upstream repositories for these files declare no licence, so there is nothing to reproduce and inventing one would misrepresent them. Terms are whatever each source repo states.

From the published model card. Full card on the HuggingFace links in the sidebar.

How it works

How video models work

Prompt / imagestart pointTemporal diffusionframes over timeVideoMP4 clipA video model generates a sequence of coherent frames from your prompt or a starting image.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys h3-vbvr for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (h3-vbvr below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/videos/generations \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"h3-vbvr","prompt":"a drone shot over a forest"}'

Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms