Image to Video
Image to video is the job of turning a single still picture into moving footage: the model reads your image, takes a written description of what should happen, and predicts the frames that follow. Upload a photo on the left, say what should move, and you get an MP4 of two to thirty seconds back in one to seven minutes, depending on the model.
Seven models run this route, all priced per second: Grok Video 1.5 from 30 credits for six seconds at 480p (its shortest clip from a picture), and for five seconds Wan 3.0 from 35, Wan 2.2 from 60, Seedance 2.0 from 75, MiniMax H3 from 80, Seedance 2.5 from 95 and Wan 2.7 from 105. Output is an MP4 with nothing burned into it; every model except Wan 2.2 adds its own audio track.
Describe motion, not the picture
The single biggest difference between a good result and a mushy one is what you put in the prompt. The model can already see your image — describing what is in it spends the prompt on information it already has, and leaves it guessing about the part it cannot see, which is what should happen next.
Compare two prompts for the same photo of a woman on a park bench. "A woman sitting on a bench in a park, autumn leaves, warm light" tells the model nothing it did not already know. "She turns her head towards the camera and smiles; leaves drift past in the foreground; the camera pushes in slowly" tells it what to generate.
- Name one camera movement: push in, pull back, pan left, tilt up, orbit. Two at once usually cancel each other out.
- Name one subject action. A list of five actions in eight seconds produces a clip where none of them completes.
- Say what is in the background that should move — water, cloth, hair, smoke, leaves, traffic. Ambient motion is what makes a clip read as footage rather than a moving photograph.
- Skip style words like "cinematic", "4K", "masterpiece". They come from still-image prompting and do nothing here; the look is set by the image you uploaded.
The second image: ending on a frame you choose
The optional second upload sets the last frame, and the model interpolates between the two. Instead of guessing where the motion should end up, it has a target — the clip starts on your first picture and arrives at your second.
This is the reliable way to get a specific result rather than a plausible one. Two shots of the same scene from slightly different angles give you a controlled camera move. A closed hand and an open hand give you the gesture. Two product shots give you a turn.
It needs the two images to be relatable: the same subject, the same lighting, the same general framing. Two unrelated pictures produce a morph, not a movement.
What the image needs to be
PNG, JPG or WebP, under 10 MB, with every side between 360 and 2000 pixels. The page checks all of this in your browser before anything uploads, so a file that is too large or too small is rejected immediately rather than after a wait and a charge.
Beyond the hard limits, sharpness matters more than resolution. A crisp 800-pixel photo animates better than a soft 1900-pixel one, because the model extends the detail it can find — and if the detail is already smeared, it extends the smear. Heavy JPEG artifacts, motion blur and aggressive phone night-mode processing all show up amplified in the output.
| Setting | Limit | Why |
|---|---|---|
| Formats | PNG, JPG, WebP | Checked by file type before upload |
| File size | Under 10 MB | Vendor limit |
| Each side | 360 to 2000 px | Below 360 there is too little detail; above 2000 is rejected |
| Length | 2 to 30 seconds by model | Drift grows with length; 5 holds a face better |
| Output | 480p to 2K MP4 | No watermark; audio on every model but Wan 2.2 |
What one clip costs
Image to video is billed per second of output, not per job, so a short test costs a fraction of a full-length take. Credits are charged when the job starts and refunded automatically if it fails.
| Model | Smallest size | 5 seconds |
|---|---|---|
| Grok Video 1.5 | 5 cr/s at 480p | 30 credits for 6 s, its minimum from a picture |
| Wan 3.0 | 7 cr/s at 480P | 35 credits |
| Wan 2.2 | 12 cr/s at 480p | 60 credits |
| Seedance 2.0 | 15 cr/s at 480p | 75 credits |
| MiniMax H3 | 16 cr/s at 768P | 80 credits |
| Seedance 2.5 | 19 cr/s at 480p | 95 credits |
| Wan 2.7 | 21 cr/s at 720p | 105 credits |
Start at 480p, then commit
Generate the shortest clip at the smallest size first, every time. On Wan 3.0 that is 35 credits for 5 seconds and three to four minutes; on Wan 2.2 it is 60 credits and about a minute; Grok Video 1.5 needs at least 6 seconds from a picture, so 30 credits. It answers the only question that matters at that point: did the model understand the motion you asked for? If it did not, the prompt is wrong and a 720p version of the same prompt will be wrong more expensively.
In our test a 1280×720 still came back as an 832×480 clip at five seconds. The framing and the motion at 480p are the same ones you will get at 720p — only the detail changes — so the cheap pass is a real preview, not a different result.
When not to use this
- Generating a scene from scratch. Every clip here starts from a picture you upload. If you have no image, use text to video instead.
- Long takes. Faces and fine detail drift the further the model gets from your first frame, and no prompt prevents it — even where a model allows 30 seconds. Generate several short clips and cut them together.
- Keeping a face exactly recognisable. Over five seconds it usually holds; over eight it often softens into someone adjacent. Treat a person’s likeness as approximate.
- Readable text. Signs, labels and captions in the source image turn to nonsense as soon as they move. Add text afterwards in an editor.
- A specific soundtrack. Most models here invent the audio from the scene and Wan 2.2 returns a silent MP4; Wan 2.7 can time the motion to a track you upload. For finished music or voiceover, add it yourself in an editor.
- A photo of somebody who has not agreed to it. Animating a real person’s picture without their say-so is not what this is for.
Questions people ask
How do I turn my photo into a video?
Upload the photo in the editor on this page, write one sentence about what should move, pick a model, a length and a size, and press Create. An MP4 comes back in one to seven minutes depending on the model, and the price is on the Create button before anything is charged: 30 credits for 6 seconds at 480p on Grok Video 1.5, 35 for 5 seconds on Wan 3.0, 60 on Wan 2.2.
Can AI make videos from photos for free?
Not completely, because every clip runs on rented GPUs. A new account gets 25 free credits: enough for a 5-second clip from a prompt on Grok Video 1.5, but not for one from a photo, where the cheapest clip is 30 credits (Grok needs at least 6 seconds when it starts from a picture). What you pay for is an MP4 with no watermark, priced per second, with no subscription required and failed jobs refunded.
How does image to video AI work?
The model does not move your photo around. It generates every frame after the first, using your picture as the starting point and your prompt as the instruction for what happens next. That is why the clip can show things the photo never contained, such as the far side of a face as it turns, and why fine detail drifts the longer the clip runs.
What kind of images work best for image to video?
Sharp ones with one clear subject. A crisp 800-pixel photo animates better than a soft 1,900-pixel one, because the model extends whatever detail it finds, blur and JPEG blocks included. Keep text out of the frame, since signs and labels turn to nonsense once they move. Files must be PNG, JPG or WebP under 10 MB, with every side between 360 and 2,000 pixels.
Can I use AI-generated images, such as Midjourney pictures?
Yes. The models only care that the still meets the file limits, not where it came from, and generating the first frame as an image is often the best start: you can get the face, wardrobe and composition right cheaply before paying for motion. Check that the image tool’s terms allow the use you have in mind.
How long does it take to generate an AI video?
One to seven minutes in our tests, depending on the model: about a minute on Wan 2.2, under two on Wan 2.7, two and a half to four on Wan 3.0 and Seedance 2.0, four to five on Seedance 2.5, and about seven on MiniMax H3. Wan 3.0’s prime mode returned a 5-second clip in 80 seconds. You can leave the page; the clip waits in History for three days.
What is the difference between image to video and text to video?
Image to video starts from a picture you supply, so the face, wardrobe and composition are settled before generation and the model only invents the motion. Text to video invents everything from the prompt, so the same prompt run twice gives two different people. If you can produce the first frame, start here; use text to video for shots you cannot picture as a still.
Related tools
Checked 17 November 2026.