Animate a portrait, product photo, or fashion still with Hailuo 2.3. Add one image, describe the movement, and choose a supported clip length and resolution.
The final cost is rounded up to whole credits.

Example output
Hailuo 2.3
Image to Video

Example output
Hailuo 2.3
Best for
Supports
Try this model
No results to display yet.
Model examples
Review examples to help decide whether the model fits your task.
Model strengths
Model strengths
Suggested uses
Tasks to consider
Model details
Provider
MiniMax
Category
Video
Capabilities
Image to Video
Credit charges
Credit rate: 25–80 per video
Inputs
1 image reference
Prompt requirements
Up to 5,000 characters
Developer access
Hailuo 2.3 can be called through Public API v1. Modes that use reference media require uploads through the Files API. Check the model reference for supported inputs.
Hailuo 2.3 FAQ
Use it when you have a still image and want to explore how it could move. For example, you could describe a slow camera move around a product or a small gesture in a portrait. The image provides the visual starting point; your prompt describes the motion.
Yes. Upload exactly one reference image and enter a prompt of up to 5,000 characters. Rivya currently offers image-to-video generation for this model, with no text-only mode.
Choose 6 or 10 seconds at 768p, or 6 seconds at 1080p. Standard and Pro both use these combinations.
These are initial estimates. Rivya reserves the estimated amount when you submit your request. Standard: 25 credits at 768p/6 seconds, 40 at 768p/10 seconds, and 40 at 1080p/6 seconds. Pro: 40 credits at 768p/6 seconds, 80 at 768p/10 seconds, and 70 at 1080p/6 seconds. After a successful generation, valid reported usage is rounded up to whole credits to determine the final charge. If it is lower than the reserve, the difference is returned. If usage is missing, invalid, or above the reserve, billing remains under review.
Start with Standard if you want the lowest credit cost. Choose Pro if you want to evaluate that quality setting for the same image and motion brief; compare the results before committing to more clips.
Choose a portrait, product photo, or fashion still with a clear subject. Ask for one main movement, such as a gentle head turn, drifting fabric, or a slow camera push. Review the result before changing the prompt or settings.
One JPG, PNG, or WebP image, no larger than 10 MiB (10,485,760 bytes). Sign in before uploading. You will also need a prompt describing the motion; a second image, video, or audio file is not accepted for this model.
Set the quality, resolution, and clip length, then review the credit estimate. Use 768p for a 6- or 10-second clip, or 1080p for a 6-second clip. Check that your prompt describes the movement you want from the uploaded image.
Sign in before uploading an image or generating a video. The initial estimate for the default Standard, 768p, 6-second clip is 25 credits; other supported settings are estimated at 40, 70, or 80 credits. That amount is reserved when you submit. After a successful generation, valid usage determines the final charge, which may be lower; any difference is returned to your balance. Billing stays under review if reported usage is missing, invalid, or exceeds the amount reserved.
Yes. Open Hailuo 2.3 in Studio to use its generation form. You can follow submitted tasks from the task-history links. Each new generation still uses one reference image and a prompt.
Compare alternatives
Create Seedance 2.5 videos from text, a start frame with an optional end frame, or image, video, and audio references. Choose 480p, 720p, or 1080p, a duration from 4 to 30 seconds or automatic duration, and an MP4 or MOV format request.
Why consider it
Input option: Up to 50 reference files
Generate video from text, a first frame, or media references.
Why consider it
Input option: Prompt, first frame with optional last frame, or image/video/audio references
ByteDance's Seedance 2.0 Fast video model for text prompts, a first frame with an optional last frame, or image, video and audio references. Choose 480p or 720p, set a 4–15-second duration, and request audio or a returned last frame.
Why consider it
Input option: Prompt, first frame with optional last frame, or image/video/audio references