It’s been quite some time since AI became capable of creating illustrations and videos, and we’ve now entered an era where anyone with an idea can bring their work to life instantly.
However, the quality of AI-generated content is often a topic of discussion.
There can still be a sense of artificiality—such as faces or clothing suddenly changing, or the audio and video not syncing properly.
Amid this, “ DomoAI ” has rolled out an update to its AI video generation feature, “Omni Reference.”
It now supports two video generation models: Seedance 2.5, which makes it easier to maintain character consistency, andMiniMax H3, which can generate visuals synchronized with audio.
DomoAI Updates “Omni Reference”; Video Generation Models Seedance 2.5 and MiniMax H3 Now Available
Seedance 2.5 is now on DomoAI.
🖼️ 30 images
🎬 10 videos
🎵 10 audio clips
50 references. One generation.
Hand it your references — images, clips, audio — and the character holds. Every shot.
Try one shot for free👇 https://t.co/NgmTYx0KbV#DomoAI#Seedancepic.twitter.com/N71iy9ByZ6— DomoAI official (@DomoAI_) August 9, 2026
” Omni Reference,” the video generation feature of ” DomoAI,” a platform that uses AI to generate videos and images,
allows users to provide specific instructions to the AI using actual reference material—such as a character’s appearance and movements, the atmosphere of a scene, and acting that matches the music—which cannot be fully conveyed through text alone.
Omni Reference has been updated to supportthe video generation models Seedance 2.5and MiniMax H3.
Seedance 2.5: Maintaining Character Consistency
Seedance 2.5 is a video generation model that maintains consistency in a character’s face, hairstyle, and costume—even as scenes and camera angles change.
For each generation, you can use up to 30 reference images, up to 10 reference videos, and up to 10 reference audio clips.
It is well-suited for works where the same character appears consistently throughout.
MiniMax H3: Characters Move in Sync with Audio
MiniMax H3 is a model that generates videos by combining visual information—such as character images and videos—with auditory information, such as music and dialogue.
It can generate videos in which characters move their mouths and facial expressions in sync with the inputted audio.
| Comparison of AI Video Generation Models | ||
|---|---|---|
| Category | Seedance 2.5 | MiniMax H3 |
| Generation Time per Request | 4–30 seconds | 4–15 seconds |
| Reference images | Up to 30 images | Up to 9 images |
| Reference videos | Up to 10 videos | Up to 3 (up to 3 items total, including audio files; total video length must be 15 seconds or less) |
| Audio files | Up to 10 entries | Up to 3 items (up to 3 items total, including reference videos) |
| Total number of reference materials | Up to 50 items (30 images, 10 videos, 10 audio files) | Up to 12 items (up to 9 images; up to 3 items total when combining videos and audio files) |
| Output resolution | 480P or 720P | 768P, up to 2K |
| Start and End Frames | Supported depending on available generation modes | Supported |
Everything is done online! Here’s how to use it
- 1. Go to DomoAI and open Omni Reference.
- 2. Upload a character image and, if necessary, add reference videos for movement or camera work, as well as music or audio.
- 3. Select either Seedance 2.5 or MiniMax H3 depending on your production goals.
- 4. Enter text describing the scene, character movements, facial expressions, camera work, and more to generate a video.
- 5. Review the generated results, adjust your reference materials or instructions as needed, and regenerate the video.
Achieve even higher quality with this update!
You can further enhance the quality of your work by using Seedance 2.5 when you want to maintain a character’s appearance, and MiniMax H3 when you want to animate characters in sync with audio.
Enjoy creating with DomoAI, which now allows you to produce even higher-quality work thanks to the latest updates!
For details on how to use DomoAI and its pricing structure, please visit the official DomoAI website.
🔥 MiniMax H3 is now live on DomoAI.
One multimodal workflow. Multiple ways to create.
✍️ Text → Video
🖼️ Image → Video
🎵 Audio → Video
🎬 Video → Video
With Omni Reference, combine up to 9 images, 3 videos, and 3 audio references in a single creation.More creative… pic.twitter.com/0vKd2W4Guo
— DomoAI official (@DomoAI_) August 18, 2026
Sorry, this article is only available in Japanese and 繁體中文. at the moment.
Generative AI in Practice: 100+ Amazing Ways Generative Artificial Intelligence is Changing Business and Society
