AI video answer
How do I prompt Hailuo 2.3 image-to-video?
Treat the uploaded image as the exact first frame. Preserve the subject, clothing, colors, composition, and main objects, then describe the new action, camera movement, and final state.
Lock the source identity
Name the face, clothing, object details, colors, and composition that must remain. The image supplies the visual evidence and the prompt tells Hailuo which parts cannot drift.
Do not replace the subject or location unless the requested transition explicitly needs that change.
Describe the motion after frame one
Move directly from the still into physical action. Separate subject motion, environmental motion, and camera motion so each part has a clear job.
Use small linked movements for portraits: breathing, blinking, a head turn, fabric movement, and one controlled camera move often read better than a crowded action list.
Choose Standard or Fast
Standard Hailuo 2.3 supports text-to-video and image-to-video. The Fast model is the lower-cost, lower-latency image-input route.
Use the same prompt structure for both, then compare motion, identity, and detail at the exact output setting you plan to buy.
Related guide
Get the full context.
Hailuo 2.3 prompt guide, camera commands, and examples
Write Hailuo 2.3 prompts with bracketed camera control, image-to-video motion, prompt optimizer guidance, and the correct 6 or 10 second output plan.
Read the hailuo 2 3 prompt guide guideCurrent prices
Compare each video route.
| Model | Compared rate | Cre8vid price | 5 sec | 10 sec | Savings |
|---|---|---|---|---|---|
| MiniMax H3MiniMax | $0.065 | $0.029 | $0.145 | $0.29 | 55% less |
| Wan 3.0Alibaba | $0.050 | $0.025 | $0.125 | $0.25 | 50% less |
| Kling 3.0Kuaishou | $0.084 | $0.039 | $0.195 | $0.39 | 54% less |
| Seedance 2.5ByteDance | $0.144 | $0.069 | $0.35 | $0.69 | 52% less |
| Veo 3.1 Fast + audioGoogle | $0.100 | $0.049 | $0.24 | $0.49 | 51% less |
Source notes