
Talking Avatar Script Board video preview showing motion rhythm, subject continuity, camera direction, and final hero frame.
Talking Avatar Script Board video brief: setup / main motion / camera path / continuity / hero ending / review checks
Hailuo 2.3 is Rivya's MiniMax image-to-video model for turning strong stills into smoother portrait, fashion, and product motion with explicit quality, duration, and resolution controls.
The final task cost is rounded up to whole credits.

Example output
Example; generating model unverified · Preview for Talking Avatar Script Board, focused on scene setup, camera path, motion continuity, editable details, and the final hero frame.
Image to Video

Example output
Example; generating model unverified · Preview for Talking Avatar Script Board, focused on scene setup, camera path, motion continuity, editable details, and the final hero frame.
Best for
Supports
Online trial
No results to display yet.
Prompt starters
Model examples
Browse template previews for ideas. Each caption indicates whether generation with this model has been verified.
Example; generating model unverified · Preview for Talking Avatar Script Board, focused on scene setup, camera path, motion continuity, editable details, and the final hero frame.
Example; generating model unverified · Preview for a high-energy keynote stage video brief, focused on scene setup, camera path, motion continuity, editable details, and the final hero frame.
Example; generating model unverified · Preview for Window Monologue Vlog Scene, focused on natural light, quiet movement, and a restrained emotional arc.
Decision fit
Decision fit
Model details
Provider
MiniMax
Category
Video
Capabilities
Image to Video
Credit model
Credit rate: 25–80 / video
Input path
1 image reference
Prompt setup
Up to 5,000 chars
Hailuo 2.3 FAQ
Use Hailuo 2.3 to animate portrait or fashion stills, create product hero loops from one reference image, and produce short social or lifestyle clips. It offers Standard and Pro quality tiers at 768p and 1080p.
On Rivya, Hailuo 2.3 currently supports image to video. It can also take one reference image.
Choose 6 or 10 seconds, Standard or Pro quality, and 768p or 1080p based on the delivery need. Start with a clean reference where the subject, background, and intended motion are easy to read.
Rivya currently lists pricing from 25 credits per generation. That cost is easier to justify once the clip is tied to animating portrait or fashion stills into motion instead of open-ended exploration. [Standard: 768P/6s=25, 768P/10s=40, 1080P/6s=40; Pro: 768P/6s=40, 768P/10s=80, 1080P/6s=70]
Choose Hailuo 2.3 when you need standard and Pro quality tiers and 768P and 1080P resolution options. If you are still narrowing down the direction, start with a lighter draft option.
Start here when the first run is aimed at animating portrait or fashion stills into motion, product hero loops from one reference image, or social teasers and short lifestyle motion clips. That keeps the first run practical: check the input, direction, and output quality here before turning it into a longer project.
This page currently supports image to video. That keeps the first result focused on whether the still, driver asset, or character setup is enough to carry animating portrait or fashion stills into motion. You can also bring in one reference image.
Before you run it, the main checks are duration choices such as 6s and 10s, output tiers like 768P, 1080P, Standard, and Pro, and reference-input quality. Those are usually the pieces that decide whether the first result is close enough that you can keep iterating here toward animating portrait or fashion stills into motion without making the setup heavier than it needs to be.
The page is public, but the actual first image-led video run is still gated behind sign in. Rivya currently lists pricing from 25 credits per generation. You can line up the still, driver asset, and duration first, then sign in when you are ready to generate the clip. [Standard: 768P/6s=25, 768P/10s=40, 1080P/6s=40; Pro: 768P/6s=40, 768P/10s=80, 1080P/6s=70]
Stay on this page while you are still validating the still, driver asset, and whether the first motion pass is enough for animating portrait or fashion stills into motion. Open the full Studio once the work needs saved versions, repeated clip iterations, multiple assets, or a longer character- or scene-based production thread.
Compare alternatives
Seedance 2.5 is Rivya's larger Seedance workflow for prompt-only video, first- and last-frame guidance, multimodal references, and video-guided transformation. It adds a 1080p tier, output up to 30 seconds, automatic duration, MP4 or MOV output, and substantially larger image, video, and audio reference capacity than Mini.
Why consider it
Consider it when your next task needs Up to 50 reference files.
ByteDance's full Seedance 2.0 video model with explicit support for prompt-only generation, frame-driven animation, and multimodal reference generation. Rivya keeps the documented role split explicit so frame inputs and multimodal references stay mutually exclusive instead of collapsing into one ambiguous upload bucket.
Why consider it
Consider it when your next task needs Prompt, frames, or image/video/audio references.
ByteDance's faster Seedance 2.0 video model with full scene routing for prompt-only generation, frame-driven image animation, and multimodal reference video generation. Rivya keeps the documented scene split explicit so first/last-frame inputs do not collide with reference image, video, and audio roles.
Why consider it
Consider it when your next task needs Prompt, frames, or image/video/audio references.
Best-fit tasks
Use it when the task looks like this