What is image-to-video generation?

Image-to-video generation animates a still image into a short video clip. The image usually becomes the first frame, and your prompt describes the motion and the camera movement, so the subject, framing and style of the picture carry into the video.

Model types

What image-to-video means

Image-to-video is a mode of video generation. Instead of creating a scene from text alone, the model starts from a picture you supply and animates it. On most models the image becomes the first frame of the clip, so its subject, framing, colors and style are where the video begins. The prompt then describes what happens next: how the subject moves, what changes in the scene and how the camera travels, for example slowly zoom out and pan right.

This gives you more control than text-to-video. You can design or approve the exact look first, often with an image generation API, and then add motion to it.

Ways a model can use your images

  • First frame. One image starts the clip, and the model animates forward from it.
  • First and last frame. On models that support it, a second image sets the final frame, and the model generates the motion between the two. This suits transitions, reveals and before-and-after shots.
  • Reference images. In reference-to-video, the images are not frames. The model carries the characters, products or style they show into a new scene, which helps keep a character consistent across several clips.
  • Talking portraits. An avatar model animates a single portrait with an audio track, or with text spoken by a built-in voice.

How an image-to-video request works

Image-to-video uses the same endpoint as other video generation, POST /v1/videos/generations. Pass the image as a public URL in image, add a prompt for the motion, and set duration and resolution. On models that take a last frame, the second image goes in its own field, such as image_end. Many models choose the mode from what you attach, and a mode parameter selects it explicitly.

The output usually follows the aspect ratio of your image, so crop the image to the shape you want, such as 9:16 for vertical video, before you send it. Each model page lists the image formats and sizes it accepts. The request runs as an asynchronous job: the API returns a job_id at once, and you poll GET /v1/jobs/{job_id} until the video is ready.

What image-to-video is used for

  • Product and ad clips. Turn a product photo into a short motion shot for a store page or a social ad.
  • Animated artwork. Add motion to illustrations, concept art and brand characters.
  • Consistent sequences. Start several clips from images of the same character or set, so the shots match when you edit them together.
  • Explainers and training. Create talking-head videos from a portrait and a script.

Choosing a model and what it costs

Test candidates with your own image, because models differ in how faithfully they keep faces, products and printed text while adding motion. Also compare first and last frame support, maximum duration and resolution, native audio and generation time. Side-by-side model comparisons help narrow the list.

Image-to-video is billed like other video generation: most models charge per second of output at a rate set by the resolution, and many use the same rate for text-to-video and image-to-video. Some models also bill input images. Browse the video models, try one in the Playground, and read the video generation reference before you call the API with your key.

Pay as you go, or choose a plan with weekly allowances. Current rates are on the pricing page.

The models on EmpirioLabs AI

20 models, cheapest first where they share a billing unit. Each model's page has its full rate card, parameters and code.

Endpoints

POST /v1/videos/generations

Priced per second

ModelLowest rateApplies to
Wan 2.2 Alibaba Cloud$0.015 per secondFlash 480P
PixVerse V6 Max PixVerse$0.030667$0.024534 per secondStandard 360p no audio
MiniMax H3 Lite MiniMax$0.025 per second480p
Pixverse Avatar PixVerse$0.025556 per second360p
Pixverse v6 PixVerse$0.025556 per secondStandard 360p no audio
Pixverse C1 PixVerse$0.030667 per secondStandard 360p no audio
Wan 2.1 Alibaba Cloud$0.036 per secondTurbo
Wan 2.5 Alibaba Cloud$0.05 per second480P
Show all 20 models
ModelLowest rateApplies to
MiniMax H3 Highspeed MiniMax$0.06 per second768p
Seedance 2.0 Mini ByteDance$0.070 per secondT2V/I2V 480P
Wan 3.0 Alibaba Cloud$0.07 per secondStandard 480P
Kling 4.0 Flash Kling AI$0.094 per secondStandard 720p
Grok Imagine Video 1.5 xAI$0.096 per second480p
Seedance 2.5 Flash ByteDance$0.135 per secondT2V/I2V 480P
HappyHorse 1.1 Alibaba Cloud$0.14 per second720p
Kling 4.0 Kling AI$0.157 per secondStandard 720p
Kling V3 Kling AI$0.168 per secondStandard T2V/I2V
Kling 3.0 Turbo Kling AI$0.18 per second720p
MiniMax H3 MiniMax$0.18 per second768p
Seedance 2.5 ByteDance$0.206 per secondT2V/I2V 480P

Frequently asked questions

What is the difference between image-to-video and text-to-video?

Text-to-video creates the scene from a prompt alone. Image-to-video starts from a picture you supply, usually as the first frame, and the prompt describes the motion.

Does the video keep the aspect ratio of my image?

On most models, yes: image-to-video follows the shape of the source image. Crop the image to the ratio you need, such as 9:16 or 16:9, before you send it.

Can I set both the first and the last frame?

Yes, on models that support it. You send a second image as the last frame, and the model generates the motion between the two images.

How much does image-to-video cost?

Most models bill per second of generated video at a rate set by the resolution, often the same rate as text-to-video. Some models also bill input images. On EmpirioLabs AI you can pay as you go or choose a plan with weekly allowances.

Ready to use better endpoints?

Check out our pricing or reach out if you want your own model deployed on our stack.