How many reference images a model takes ranges from 3 to 14 among the models on 8frame. For images, Seedream takes the most (14), then Nano Banana and GPT Image (10 each). For video, Grok Imagine's reference mode takes 10, Happy Horse 9, Gemini Omni Flash and Kling O1 7. Seedance is the odd one: version 2.5 itself accepts up to 30, but the canvas lets you attach 9.
TL;DR
- Image models: Seedream 14, Nano Banana 10, GPT Image 10, Reve 6, Grok Imagine Image 3, Qwen Image 3 (edits) 3.
- Video models: Grok Imagine reference mode 10, Seedance 9 on the canvas, Happy Horse 9 (5 when editing a video), Gemini Omni Flash 7, Kling O1 Reference 7.
- Seedance 2.5 can also take reference video and audio: up to 10 clips of up to 30 seconds each, and up to 10 audio tracks.
- More references is not automatically better. Each one is another thing the model has to reconcile; use the fewest that pin down what must not change.
Image models
| Model | Max reference images |
|---|---|
| Seedream (5 Pro, 5, 4) | 14 |
| Nano Banana (Classic, 2, Pro) | 10 |
| GPT Image | 10 |
| Reve | 6 |
| Grok Imagine Image | 3 |
| Qwen Image 3 (editing) | 1 to 3 |
Grok Imagine Image's 3 is the provider's own cap; its schema says "A maximum of 3 images are supported".
Video models
| Model | Max reference images | Other references |
|---|---|---|
| Grok Imagine (reference mode) | 10 | |
| Seedance 2.5 | 9 on the canvas (the model accepts 30) | up to 10 videos of up to 30 s, up to 10 audio tracks |
| Seedance 2.0 | 9 | up to 3 videos of up to 15 s, up to 3 audio tracks |
| Happy Horse (reference to video) | 1 to 9 | |
| Happy Horse (video edit) | up to 5 | the video being edited, 3 to 60 s |
| Gemini Omni Flash | 1 to 7 | |
| Kling O1 Reference | up to 7 |
Happy Horse's reference-to-video is built for characters: each reference is a person or figure it keeps consistent across the clip. It costs 95 credits for 5 seconds at 720p and 189 at 1080p.
Which references to use, and how many
References do three different jobs, and it helps to decide which job each image is doing before you attach it:
- Identity: the person, character or product that must look the same. Start with one clean image per subject.
- Style: a palette, lighting or finish to copy. One or two frames.
- Layout: a composition or a start frame. Usually one.
A practical ceiling for most shots is one image per subject plus one for style. Add more only when a specific detail keeps drifting, and then add the image that shows that detail.
Faces as references
If a reference shows a face in close-up, Seedance's filter may reject the run. A waist-up shot of the same person passed in our tests; see Seedance "flagged as sensitive" (E005). The other size and format rules for reference images are in upload limits by model.
FAQ
How many reference images can Nano Banana use? Up to 10.
How many reference images does Seedance accept? On the 8frame canvas, 9 for both 2.0 and 2.5. Seedance 2.5 itself accepts up to 30.
Which AI video model takes the most reference images? Grok Imagine's reference mode, with 10. Happy Horse takes up to 9 character references.
How many reference images does Gemini Omni Flash take? Between 1 and 7.
One reference per subject, one for style, and add more only when a detail drifts. The 8frame canvas is free and unlimited, and generation is paid from $19/month.