Skip to main content

WAN 2.7 Image-to-Video

AI Generated

Generated on PixelDojo with WAN 2.7 Image-to-Video. Produced by PixelDojo's generation pipeline.

Cancel anytimeCommercial-use license50+ AI models

WAN 2.7 Image-to-Video costs 2.5 credits per second at 720p, so our 2 second minimum run cost 5 credits and took about 39 seconds on August 26, 2026. It animates a starting image into a short clip, and it also handles video continuation on the same endpoint. This page covers the price, the measured speed, a resolution detail our own file check turned up, and how it compares with the text-to-video sibling on the same tool.

The product orbit clip, five credits

Every example below was produced on PixelDojo. Hover to see the prompt.

Slow cinematic camera orbit around the earbuds case, soft studio lighting shifts, the lid opens gently to reveal the earbuds, product commercial style

WAN 2.7 Image-to-Video

What the image-to-video path adds over text-to-video

2.5 credits per second at 720p

The same per-second rate as WAN 2.7 Text-to-Video on the same underlying tool. Duration runs 2 to 15 seconds, so the floor is 5 credits at 2 seconds.

720p requested, a 960 square frame returned

We set resolution to 720p, which is a 1280 by 720 landscape tier. The source image was a square product photo, and the clip that came back was 960 by 960, matching the input's own aspect ratio rather than the requested landscape tier.

What the file measured

960 by 960, exactly 2.0 seconds, 30 frames per second, 690 kilobytes, well under a megabyte for the 2 second minimum.

Also does video continuation

The same endpoint has a video-extend mode that continues an existing clip rather than a still image, with its own duration and source-length rules.

Last-frame control and audio sync

An optional last_frame_url can pin where the motion ends, and an audio_url can drive the pacing. Neither was used on this test run.

Much faster than the text-only mode in our test

39 seconds against 224 seconds for the text-to-video mode on the same underlying model, on the same day. Starting from a real image appears to shortcut a slower path that pure text generation takes.

Why Choose Pixel Dojo for WAN 2.7 Image-to-Video

Professional-quality results with cutting-edge AI technology

5 credits for the cheapest clip

2 seconds at 720p is the lowest cost combination the schema allows for this model.

About 39 seconds, measured

Timed on August 26, 2026 from request to finished file, well inside the API's synchronous response window.

Small file size at the minimum duration

690 kilobytes for the full clip, cheap to store and quick to preview.

How It Works

How we ran it, so the numbers are reproducible:

1

Start from a real image

We used a studio product still as the source frame, not a blank prompt.

2

Set duration and resolution to their floor

2 seconds and 720p is the cheapest combination the schema allows, and it is what we timed and charged, even though the output came back square rather than the 720p landscape tier.

3

Run it in the app or over the API

Generate from the WAN 2.7 Video tool page, or POST to /api/v1/models/wan-2.7-i2v/run. Ours took about 39 seconds and charged 5 credits.

Animate an image with WAN 2.7

Loved by creators on PixelDojo

Real feedback from people using PixelDojo, pulled from our in-product surveys.

Love you guys!!
Verified PixelDojo creator
Trained my Lora super fast. Still working out how to creat content wit it, but I love it so far.
Verified PixelDojo creator
I love this app
Verified PixelDojo creator
It has all the tools I can think of...
Verified PixelDojo creator
deployment rate of splendid features is incredible. Legend
Verified PixelDojo creator
large selection of tools on one platform
Verified PixelDojo creator

Common Questions

Everything you need to know about WAN 2.7 Image-to-Video

What does WAN 2.7 Image-to-Video cost?

2.5 credits per second at 720p, the same rate as the text-to-video mode on the same tool. Duration runs 2 to 15 seconds, so the cheapest job is the 2 second clip at 5 credits.

How fast is WAN 2.7 Image-to-Video?

About 39 seconds in our August 26, 2026 run, from request to a finished file. That was well under the text-to-video mode's 224 seconds on the same day, same underlying model.

Why did a 720p request return a square video?

Our source image was square. The clip came back at 960 by 960 rather than the 1280 by 720 the 720p tier implies for a landscape input. In image-to-video mode, output aspect appears to follow the source image rather than overriding it to the requested tier's default shape.

How does it differ from WAN 2.7 Text-to-Video?

Image-to-Video requires a starting image and, in our test, returned a result much faster than the text-only mode. Text-to-Video needs no image but generates purely from the prompt, and ran slower in this same-day comparison.

How does it compare to WAN 2.6 Flash?

WAN 2.6 Flash also does image-to-video, at 1 credit per second against this model's 2.5, but drops video-extend and last-frame control. This model costs more per second and adds those two capabilities on the same endpoint.

How do I call it from the API?

POST to /api/v1/models/wan-2.7-i2v/run with your API key, an image_url, and a prompt. It is the same key and request shape as every other model in the catalog.

Compare every video model on price

Ready to Create Amazing WAN 2.7 Image-to-Video Images?

Join thousands of creators using AI to bring their ideas to life