Hailuo 02 is a cinematic video generation model from MiniMax. It accepts text prompts and reference images as input and generates video output, supporting both text-to-video and image-to-video workflows. Built on MiniMax's NCR (Noise-aware Compute Redistribution) architecture, it delivers high-resolution output up to 1080p (with 512p and 768p options) and camera-aware generation, with a focus on realistic physics, frame consistency, and film-like visual fidelity. It is suited for cinematic scene generation, creative content production, and physics-driven motion such as acrobatics and complex action.
Generate video
All API requests must be authenticated using a Bearer token in the Authorization header. Please ensure your API key is active.Authorization: Bearer sk-xxxxxx
These parameters come from the selected model form_schema. Switching models updates this list and the request example.
Choose the generation mode. Text to Video: prompt only. Image to Video: one image as the first frame. First-Last Frame: upload a first and last frame for a transition video. Hailuo-02 supports all three.
prompt*stringText prompt, max 2000 characters. Required in Text-to-Video mode, optional in other modes.
duration?stringVideo duration in seconds, 6 or 10, default 6. Only 6 seconds is supported at 1080p.
resolution?stringVideo output resolution, 768p or 1080p, default 768p. 1080p supports only the 6-second duration.
prompt_optimizer?booleanWhether to automatically optimize the prompt. When on, the system rewrites the prompt to improve results. Enabled by default.
aigc_watermark?booleanWhether to add an AIGC watermark to the generated video. Disabled by default.
task_id?stringParameter description for Task Id
status?stringParameter description for Status
error?objectParameter description for Error
message?stringError Message
type?stringError Type
param?stringRelated Parameters
code?stringError Code