Model reference · open weights
minimax-h3-4step-lora-flashgen is an open-weight video model from Beidouqixing, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
MiniMax-H3 4-Step LoRA (FlashGen) 4-step distilled LoRA for MiniMax-H3 text-to-video+audio (T2VA). Trained on Ascend NPU with data-free distillation; merge into the base model and inject baseschedule before vllm-omni / MindIE-SD deployment. Files Training config Usage Requires base model MiniMaxAI/MiniMax-H3. Merge with mergelorackpt.py before vllm-omni / MindIE deployment: Deployment (MindIE-SD / vllm-omni) For Ascend NPU inference and serving, see the MindIE-SD deployment guide: - MiniMax-H3 推理部署文档（含 4 步蒸馏权重合并与启动） - MindIE-SD 仓库：Ascend/MindIE-SD
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | Beidouqixing |
|---|---|
| Type | Video models |
| Variants | 1 |
| Runs with | minimax-h3 |
| Based on | MiniMaxAI/MiniMax-H3 |
| Released | 2026-08-24 |
| Popularity | 2k downloads / month |
| Likes | 13 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| minimax-h3-4step-lora-flashgen | — | BF16 | — | — | Weights ↗ |
Using it via the API
Once AxForge deploys minimax-h3-4step-lora-flashgen for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (minimax-h3-4step-lora-flashgen 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":"minimax-h3-4step-lora-flashgen","prompt":"a drone shot over a forest"}'
Details
Languages
Tags
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗
Explore