Video Reference Images
Generated on PixelDojo. Produced by PixelDojo's generation pipeline.
Eleven video models on Pixel Dojo accept reference images: several pictures that describe a subject, rather than one picture the model animates. Caps run from three references on VEO 3.1 Standard up to thirty on Seedance 2.5. A reference is a different input from the start frame most image-to-video models take, and the field name matters. Both lists are below, with the field each model expects.
The eleven models that take true reference images
Seedance 2.5: up to 30 reference images
The largest reference budget in the catalog by a wide margin, sent as reference_images. It also takes reference videos and reference audio in the same request, and the prompt can address them by name so you can tell the model which reference to use for what.
WAN 3.0: up to 10 reference images
Sent as reference_image_urls, alongside optional reference video and reference audio arrays of up to five each. The prompt syntax lets you point at a specific reference, so one call can carry a face, a set and a voice.
MiniMax H3: up to 9 reference images
Sent as reference_images to guide subject and scene identity, alongside reference videos and reference audio. References and the start and end frame fields are separate modes on this model: pick one per request. H3 Fast and P-Video 2 Pro Reference take the same reference set at a lower rate.
Seedance 2 Reference: up to 9 reference images
A reference-only entry point, sent as reference_images. The request is rejected unless at least one reference image or reference video is present, so there is no accidental text-to-video fallback.
Happy Horse Reference: 1 to 9 reference images
Sent as reference_urls, with at least one required. Clip length runs from 3 to 15 seconds at 720p or 1080p.
Grok R2V: 1 to 7 reference images
Sent as reference_urls, at least one required, clips of 1 to 10 seconds. Room for a character plus a couple of scene cues.
WAN Reference to Video: up to 5 references
Sent as reference_urls, and the five slots are shared between images and clips, with up to three of them video. Durations are 5 or 10 seconds, with a multi-shot mode that composes a sequence across your references.
Kling Reference to Video: up to 4 reference images
Sent as image_urls. A mode switch picks image references or video references, with native audio on image references.
VEO 3.1 Standard: up to 3 reference images
Sent as reference_images, for style guidance. VEO 3.1 Standard is the tier that takes them.
P-Video 2 Pro Reference: up to 9 reference images
Built on MiniMax H3: up to nine reference_images, three reference_videos and three reference_audios, plus optional start and end frames, from 1.25 credits a second. Turn on keep_audio and the clip lip-syncs to your own song or line, which is why it powers the music videos.
Thirty references on Seedance 2.5, ten on WAN 3.0, nine on MiniMax H3, three on VEO 3.1 Standard. All eleven run on one Pixel Dojo credit balance.
Why Choose Pixel Dojo for Video Reference Images
Professional-quality results with cutting-edge AI technology
References describe a subject, a start frame describes a shot
Send references when the character or product has to survive into a scene you are describing in words. Send a start frame when you already have the exact opening image and want motion added to it.
The cap tells you what the model is for
A three image cap is style guidance. A nine or ten image cap is identity work. A thirty image cap is closer to a small asset library, which is why the highest caps sit on the models built for multi shot sequences.
The field name is part of the answer
reference_images, reference_image_urls, reference_urls and image_urls all mean the same thing to a person and different things to a server. The field name above is the one that model's schema actually validates. Single start frame models are the other camp: WAN 2.7, WAN 2.6, WAN 2.2, Vidu Q3, Seedance 1.5, Seedance 2, Grok Video, FLUX 3 Video and Gemini Omni Flash read one image field, Hailuo 2.3 names it first_frame_image, and Kling Video and PixVerse V6 add a last frame.
Save a character once, use it everywhere
Character Studio saves your character with its photos. Type @Name in any prompt and those photos ride into the model's reference field automatically, on every model above.
Free to start, unlimited to stay
3 free video effects every day, no card needed. Plans from $10/mo, Unlimited on every plan, and credits roll over every month while you are subscribed.
How It Works
Getting a reference driven clip right on the first attempt:
Decide which input you actually need
If you want your exact picture to move, use the start frame field. If you want the subject from your pictures to appear in a scene you are writing, use the reference field. On MiniMax H3 these two are mutually exclusive, so choosing up front avoids a rejected request.
Stay inside the model's cap
Three on VEO 3.1 Standard, four on Kling Reference to Video, five on WAN Reference to Video, seven on Grok R2V, nine on Happy Horse Reference, MiniMax H3, H3 Fast, P-Video 2 Pro Reference and Seedance 2 Reference, ten on WAN 3.0, thirty on Seedance 2.5. Over the cap the schema rejects the call before anything is charged.
Name the references in the prompt where the model supports it
WAN 3.0, Seedance 2.5 and Seedance 2 Reference all let the prompt address a specific reference. Saying which image the character comes from is more reliable than hoping the model infers it.
Loved by creators on PixelDojo
Real feedback from people using PixelDojo, pulled from our in-product surveys.
the amount you can do on this site
all in one place
It is a lot of fun to uae and easy too.
So many different models to try out
You keep adding to it to stay up to date and that is GOLD.
very easy to use and good support
Explore more AI tools on PixelDojo
Popular AI Models
AI Tools
Compare & Switch
- All AI Tool Alternatives
- Pollo AI Alternative
- PixelDojo vs Pollo AI
- Pollo AI Review
- MotionMuse AI Alternative
- MioCreate Alternative
- Dessi AI Alternative
- Runway Alternatives
- CapCut Alternatives
- Leonardo Alternatives
- OpenArt Alternatives
- Midjourney Alternatives
- Canva AI Alternatives
- Pika Alternatives
- InVideo Alternatives
- Higgsfield Alternatives
- Krea Alternatives
- Luma Alternatives
- Magic Hour Alternatives
- HeyGen Alternatives
- PixAI Alternatives
- Vidu Alternatives
- Seedream Alternatives
- Tensor.Art Alternatives
Common Questions
Everything you need to know about Video Reference Images
Which AI video model accepts the most reference images?
Seedance 2.5, at up to 30 reference images in one request. WAN 3.0 is next at 10, and MiniMax H3, H3 Fast, P-Video 2 Pro Reference, Seedance 2 Reference and Happy Horse Reference all take 9.
Does VEO 3.1 accept reference images?
VEO 3.1 Standard does, up to three, for style guidance. VEO 3.1 Fast and VEO 3.1 Lite work from a start frame.
What is the difference between a reference image and a start frame?
A start frame is the first frame of the clip, so the model animates that exact picture. A reference image describes a subject the model should build into a new scene, and the composition comes from your prompt instead. Models that take references usually accept several; start frame models take one.
Which video models let me fix the last frame as well as the first?
Kling Video takes end_image_url alongside start_image_url, PixVerse V6 takes last_frame_image alongside image, and MiniMax H3 takes end_image_url alongside image_url. That is the way to control where a clip lands, not just where it starts.
Will my character stay the same across clips?
Yes. Character Studio locks the face across every image and video: save the character once and type @Name in any prompt. Train a LoRA when you want it perfect.
Is it free?
Yes, to start. A free account gets 3 free video effects every day, no card needed. Plans from $10/mo unlock every model, with Unlimited on every plan and credits that roll over every month while you are subscribed.