Access

AI video answer

Which MiniMax H3 prompt mode should I use?

Short answer

Use T2VA for text only, I2VA for an exact first frame, FL2VA to connect exact first and last frames, L2VA to land on an exact final frame, and Ref2VA for full multimodal references.

01

Choose text or a keyframe mode

Choose T2VA when words define the full shot. Choose I2VA when Picture 1 is the exact opening frame and the action develops forward from it.

Choose FL2VA when both endpoints must match. Choose L2VA when the model must invent a plausible opening and converge on the supplied last frame.

02

Use full-reference mode for relationships

Choose Ref2VA when images, video, or audio control subjects, motion, camera language, editing, continuation, voice, music, or other reusable traits.

The official reference format includes subject definitions, a task summary, retention analysis, detailed description, soundscape, and music.

03

Do not mix the schemas

Base and keyframe modes use the three core fields. Full-reference mode uses six ordered sections and stable labels such as Picture 1, Video 1, and Audio 1.

Pick the mode before writing. This prevents a reference relationship from being lost inside a text-only format.

Related guide

Get the full context.

MiniMax H3 prompt guide and templates

Write MiniMax H3 prompts for 4–15 second video up to 2K with native stereo sound, keyframe control, and image, video, or audio references. Copy three templates.

Read the minimax h3 prompt guide guide

Current prices

Compare each video route.

Open full pricing →
ModelCompared rateCre8vid price5 sec10 secSavings
MiniMax H3MiniMax$0.065$0.029$0.145$0.2955% less
Wan 3.0Alibaba$0.050$0.025$0.125$0.2550% less
Kling 3.0Kuaishou$0.084$0.039$0.195$0.3954% less
Seedance 2.5ByteDance$0.144$0.069$0.35$0.6952% less
Veo 3.1 Fast + audioGoogle$0.100$0.049$0.24$0.4951% less