Creator
$19/month
Billed monthly
For solo creators posting every week
500 credits every month
- Up to 250 AI images
- Up to 50 Wan 2.7 clips
- Up to 1.5 hours of AI voiceover
- Roll over up to 1,000 credits
Wan 2.7 image to video
Wan 2.7 is Alibaba's video model. Add your photo as the first frame, add a second as the last if you like, and get a 2 to 15 second clip with sound at up to 1080p. Alibaba's open weights stop at Wan 2.2, so Wan 2.7 runs hosted, here in your browser.
Plans from $19 a month, with commercial use and no watermark.
Handheld phone selfie, shaky. She shouts over the wind, breathless: "It's right there!", then swings the camera around to the tornado as a gust tears across the wheat and rain spatters the lens. Sound: roaring wind, rain hitting her jacket, her laugh.
- Length
- 2 to 15 seconds
- Resolution
- 720p or 1080p, same price
- Cost
- About 91 cents for 5 seconds of video on the $19 plan
- Sound
- In every clip, or led by your track
- Starts from
- Text, frames, or 5 references
- Also makes
- Images, Regular or Pro
One idea, four hops.From a sentence to a shot, all on Wan 2.7.
Wan 2.7 Image drew the first frame, then edited it into the last. Wan 2.7 made the eight seconds between them.
- 01
A sentence
Your idea
“A man sits still as his room floods red.”
- 02
The first frame
Wan 2.7 Image Pro, from text
A man in his thirties in a black suit and a white shirt sits very still on a wooden chair in the middle of a small empty room tiled floor to ceiling in white. Ankle-deep clear water covers the floor and mirrors him. One bare fluorescent tube overhead casts a cold green-white light. Symmetrical wide shot at eye level, the chair centered, a closed white door behind him. Music video still, 35mm film, cinematic.
- 03
The last frame
Wan 2.7 Image Pro, an edit of the first
The same room from image 1, flooded. The water now fills the room to the height of the door handle and covers the chair and the man's body up to his chest, so only his shoulders and head show above the surface. He still faces the camera, calm. The fluorescent tube glows deep red and lights the tiles and the water red. Keep the room, the man, the door and the camera position exactly as they are.
04
The clip
Wan 2.7, 8 seconds between the two
Frame 02 as the first frame, frame 03 as the last, and this prompt:
Fixed camera, camera static, symmetrical wide shot. The fluorescent tube flickers, then turns deep red. Water pours in under the door and the room floods fast, rising up the tiles and over the chair until it reaches the man's chest. He never moves and keeps looking straight ahead. Sound: the tube buzzing and clicking, water rushing in, one deep bass hit as the light turns red. No dialogue.
Three more ways in.A sentence, a voice, or five references.
A sentence
Up to 15 seconds
Describe the subject, the action, the camera and the sound. Wan 2.7 takes up to 5,000 characters.
A summer evening on a city block, street culture. Shot 1 [0-4s] Low wide shot at golden hour: two women in baggy streetwear turn two long ropes in a fast double-dutch rhythm while a crowd of friends claps around them, a boombox on the curb. Shot 2 [4-7s] Hard cut, low tracking shot circling the jumper: a young man in a white tank top and a gold chain jumps in, spins, drops into a push-up and springs back up between the ropes. Shot 3 [7-10s] Medium shot from behind the crowd: he jumps out clean, the crowd screams and mobs him, someone throws a cap into the air. Sound: ropes slapping the asphalt in rhythm, a boom bap beat from the boombox, clapping, one shout: "Let's go!"
Start photo
A voice or a song
Tracks up to 30 seconds
Add a start photo and a sound file as driving audio. Wan 2.7 makes the clip to match it.
He raps the verse straight into his phone camera, nodding to the beat, his free hand moving with the words, a dryer spinning behind him. Handheld selfie framing, slight shake.
Image 1 
Image 2 
Image 3
Up to five references
Several shots, up to 10 seconds
Add up to five photos or clips and name them in the prompt as Image 1 or Video 1. Turn on multiple shots and Wan 2.7 cuts between angles.
Image 1 wears the red vinyl trench coat from Image 2 and walks through the car wash from Image 3 at night. Shot 1 [0-4s] Wide shot from the tunnel entrance: she walks toward the camera between the spinning pink and blue brushes, foam falling around her. Shot 2 [4-7s] Hard cut, close-up: she turns her head to the lens as water spray beads on the glossy red coat. Shot 3 [7-10s] Low angle from behind: she walks out of the tunnel into the rain, the coat swinging. Sound: brushes whirring, water hissing, a slow heavy bass beat.
Wan 2.7 makes pictures too.Wan 2.7 Image, Regular or Pro.
Make up to four pictures from one prompt, or edit up to four of your own. Pro is the higher quality level and costs more per image.
Regular 
Pro
One prompt, the same seed, both levels.
Portrait photo of a boatbuilder in his seventies with a white beard and rolled shirt sleeves, planing the wooden hull of a small rowing boat in his workshop. Curls of pale wood shavings fall from the plane. Late afternoon light through a dusty window catches the sawdust in the air. Clamps and hand tools hang on the wall behind him.
Edit with up to four of your images.
Image 1 
Image 2 
Image 3
The man from image 1 wears the camel coat from image 2, buttoned, over a dark sweater, and stands on the rainy platform from image 3 under the lamp, holding a folded black umbrella and looking down the tracks. Evening light and rain. Full-length photo.
Wan 2.7 next to Wan 3.0
Wan 3.0 is the newer Wan and runs twice as long. Wan 2.7 makes 1080p for the price of 720p and comes with an image model.
Simple pricing that scales with you.
Pick the plan for how much you post. Every model on every plan. Unused credits roll over. Cancel anytime.
Pro
Most popular$49/month
Billed monthly
For creators posting daily across channels
1,300 credits every month
- Up to 650 AI images
- Up to 130 Wan 2.7 clips
- Up to 4 hours of AI voiceover
- Roll over up to 2,600 credits
Studio
$99/month
Billed monthly
For brands and production teams
2,700 credits every month
- Up to 1,350 AI images
- Up to 270 Wan 2.7 clips
- Up to 9 hours of AI voiceover
- Roll over up to 5,400 credits
Scale
$199/month
Billed monthly
For agencies running always-on content
5,500 credits every month
- Up to 2,750 AI images
- Up to 550 Wan 2.7 clips
- Up to 18 hours of AI voiceover
- Roll over up to 11,000 credits
Every plan includesEvery model, 90+ and countingReusable AI personasSceneform Studio editorCommercial usage rights
Want checkout, comparison tables, or a custom volume? See the full pricing page
Wan 2.7 FAQ
Wan 2.7 is a video and image model from Alibaba's Wan family. On Sceneform, Wan 2.7 makes clips of 2 to 15 seconds at 720p or 1080p from text, a first and last frame, a driving track, or up to five references. Wan 2.7 Image makes and edits pictures in the image tool.
Yes. Add your photo as the first frame and describe what happens next. You can add a second photo as the last frame, and Wan 2.7 fills the clip between them. The clip keeps your photo's shape and runs 2 to 15 seconds.
Wan 2.7 Image is the image side of Wan 2.7. It makes up to four pictures per prompt, and it edits up to four of your own images, which you name as image 1 to image 4 in the prompt. Pro is the higher quality level and costs more per image. Both make square, wide, and tall pictures.
Alibaba has not published Wan 2.7's weights. Its open releases on Hugging Face (Wan-AI) and GitHub (Wan-Video) stop at Wan 2.1 and 2.2, which run in ComfyUI on your own graphics card (checked November 5, 2026). Wan 2.7 runs as a hosted model, so on Sceneform you open it in your browser with nothing to install.
2 to 15 seconds, picked to the second. With references the limit is 10 seconds. Clips come out at 720p or 1080p, and 1080p costs the same as 720p.
Yes. Wan 2.7 clips come with sound, so describe what you want to hear in the prompt. You can also add your own voice or song, up to 30 seconds, as driving audio, and the clip is made to match it.
Yes. Add up to five photos or clips as references and name them in the prompt, such as Image 1 for the person and Image 2 for the coat. Use the same references in every clip. References can't be combined with a first frame or a driving track.
Use Wan 2.7 for clips up to 15 seconds at 1080p, where it costs half as much as Wan 3.0, and when a song or voice track should lead the motion. Use Wan 3.0 for clips up to 30 seconds or more than five references. The Wan video page compares every Wan version.
Plans start at $19 a month for 500 credits. A Wan 2.7 clip costs 10 credits for 2 seconds, 24 for 5, 48 for 10, and 71 for 15, at 720p or 1080p, so the Creator plan covers fifty 2-second clips. A Wan 2.7 Image costs 2 credits, or 4 at Pro. The exact cost shows before you generate.
Yes. Every paid plan includes commercial use, and your downloads have no watermark.
A first frame, a last frame, and the shot between.
Wan 2.7
Plans from $19 a month.