Image-Text-to-Video
Diffusers
Safetensors
MiniMaxH3ModularPipeline
text-to-video
image-to-video
video-to-video
text-to-audio-video
image-to-audio-video
image-text-to-audio-video
video-to-audio-video
audio-to-audio-video
audio-video-generation
multimodal
synchronized-audio-video
reference-to-audio-video
Instructions to use MiniMaxAI/MiniMax-H3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use MiniMaxAI/MiniMax-H3 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("MiniMaxAI/MiniMax-H3", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
| set -euo pipefail | |
| # Create a 5-second 2K Ref2VA video directly and capture its runtime task ID. | |
| task_id=$( | |
| curl --silent --show-error \ | |
| --request POST \ | |
| --url "$MINIMAX_API_BASE/v2/video_generation" \ | |
| --header "Authorization: Bearer $TOKEN" \ | |
| --header 'Content-Type: application/json' \ | |
| --data '{ | |
| "model": "MiniMax-H3", | |
| "content": [ | |
| { | |
| "type": "text", | |
| "text": "Character speaks: Follow the wind, live free. Leave worries behind, enjoy the moment. Voice timbre follows reference audio 1." | |
| }, | |
| { | |
| "type": "video_url", | |
| "video_url": { | |
| "url": "https://cdn.hailuoai.com/prod/hailuo_demo/testsets/h3_promo_eval_ref2va/gallery/sr_v2p26_trio_seed42_20260724/inputs/297573323635_00_%E8%A7%86%E9%A2%911_YnyRbxEwio_video_20260525_163755_1927e9d3.mp4" | |
| }, | |
| "role": "reference_video" | |
| }, | |
| { | |
| "type": "audio_url", | |
| "audio_url": { | |
| "url": "https://cdn.hailuoai.com/prod/hailuo_demo/testsets/h3_promo_eval_ref2va/gallery/sr_v2p26_trio_seed42_20260724/inputs/f463d523c5ce_01_%E9%9F%B3%E9%A2%911_RSLcbpzJPo_6%E6%9C%885%E6%97%A5(1).mp3" | |
| }, | |
| "role": "reference_audio" | |
| } | |
| ], | |
| "resolution": "2K", | |
| "duration": 5, | |
| "ratio": "adaptive" | |
| }' | | |
| jq -er '.task_id' | |
| ) | |
| # Query again while the task is queued or running. | |
| generation_result=$( | |
| curl --silent --show-error \ | |
| --request GET \ | |
| --url "$MINIMAX_API_BASE/v2/query/video_generation/$task_id" \ | |
| --header "Authorization: Bearer $TOKEN" | |
| ) | |
| echo "$generation_result" | jq '{status: .task.status}' | |
| # Download the 2K MP4 after the task succeeds. | |
| video_url=$(echo "$generation_result" | jq -er '.task.content.url') | |
| curl --location "$video_url" --output r2va_direct_2k.mp4 | |