Wan, Tongyi Wanxiang text-to-image
This image page is Wan’s stills API, not the video family. Alibaba’s Tongyi Wanxiang text-to-image on Model Studio names wan2.2-t2i-flash and wan2.2-t2i-plus (width and height 512–1440, default 1024×1024, PNG, n=1) and wan2.6-t2i (total pixels between 1280×1280 and 1440×1440, aspect 1:4 to 4:1). That is a still from a prompt. The video Wan page on this site is the other product: Wan 3.0 (4–30s) and Wan 2.7 (2–15s) clips this site actually runs. It is not Topaz’s desktop upscaler, and it is not Uizard’s UI Autodesigner. ImgToVid does not run Wan t2i; the generator on this page drafts on GPT Image 2.5 Flare.
01 — Capabilities
A text-to-image API, not a 4K picker here
Public Wan t2i docs sell a still from a prompt on Alibaba Model Studio. They do not sell this site’s Nano Banana 4K table, and they are not the Wan 3.0 clip this site generates.


01
wan2.2-t2i-flash and plus: 512–1440px a side, default 1024×1024
PNG, one still per call (n=1) named. That generate stays on their API. This page does not open that key.

02
wan2.6-t2i: 1280×1280 to 1440×1440; aspect 1:4 to 4:1 named
A still, not a 4–30s clip. Delivery stays on Model Studio.

03
Not the Wan 3.0 / 2.7 video family this site runs
Video Wan on ImgToVid is 4–30s (3.0) or 2–15s (2.7) with audio. This image page is t2i stills, marked coming soon.

04
Not Topaz’s photo enhance, not Uizard’s UI mockups
Topaz upscales a photo you shot. Uizard builds app screens. Wan t2i is a still from a prompt. This site does not open Wan t2i.
02 — Prompt to output
Prompts that match the stills above
Each prompt describes the picture on its card. “Use this prompt” sends that text to Create. The generator on this page runs GPT Image 2.5 Flare, not Wan t2i.
01 · PortraitPromptClose photographic portrait of a young man with curly hair wearing a grey knit sweater, soft window light, he glances aside and smiles warmly, shallow depth of field.
02 · ProductPromptA clean white leather sneaker on a pale grey seamless studio backdrop, soft diffused light, three-quarter view, crisp stitching, minimal commercial photograph.
03 · StreetPromptPhotographic view down a cobblestone lane in an old European village, climbing roses on stone walls, café tables in morning sun, a few people strolling in the distance.
04 · CharacterPromptPhotograph of a young woman with shoulder-length brown hair in an olive t-shirt, golden late-afternoon light, she turns her head and looks into the distance, breeze in her hair.
03 — Where it fits
Jobs a Wan t2i API is selling
Public docs point at a 1024 still or a 1440×1440 wan2.6 still from a prompt. They do not sell a Wan 3.0 clip on this site, and they do not sell a one-shot Nano Banana still here.

A still from a prompt on wan2.2 flash or plus
That job is Alibaba Model Studio. This page does not open that API.

A wan2.6 still up to 1440×1440, aspect 1:4 to 4:1
Delivery stays on their t2i API. Not a 4–30s video generate this site already runs.

One PNG per call (n=1) named
Named on the t2i reference. Not a 4K Pro still here.

A draft still on ImgToVid
Write the still here. GPT Image 2.5 Flare carries the prompt into Create. Membership and credits are checked there.
04 — Verdict
What Wan image actually is
Strengths
- Alibaba Tongyi Wanxiang t2i: wan2.2-t2i-flash / plus and wan2.6-t2i named
- wan2.2: 512–1440px a side, default 1024×1024, PNG, n=1 still listed
- wan2.6: 1280×1280–1440×1440 and 1:4–4:1 named
- Honest that this is stills, not the Wan 3.0 / 2.7 video family this site runs
Trade-offs
- 1440×1440 is named — not a 4K still picker here
- A Wan t2i job is not a one-shot still here, and not a Wan 3.0 clip
- Wan t2i is not available on ImgToVid
- Marked coming soon on this site
05 — Side by side
Wan t2i, Nano Banana 2 and GPT Image 2.5
Wan on this page is Alibaba’s text-to-image API, not the video family. Nano Banana 2 and GPT Image 2.5 numbers below are from those vendors’ public docs on ImgToVid. A 1440×1440 wan2.6 still there is not a 4K still row here.
06 — How it works
Start a still on ImgToVid
Step 1
Describe one still
Subject, light, frame. Wan t2i will not be the model that runs it.
Step 2
Use the generator on this page
It runs GPT Image 2.5 Flare, because Wan t2i is not offered here. The prompt and the settings carry into Create.
Step 3
Generate in Create
Membership and credits are checked there. Coming back to this page does not switch the model over to Wan t2i.
07 — FAQ
Wan image, in plain terms
What is Wan on this image page?
Wan here is Alibaba’s Tongyi Wanxiang text-to-image API: wan2.2-t2i-flash / plus and wan2.6-t2i on Model Studio. It is not the Wan 3.0 / 2.7 video family this site runs. ImgToVid does not host Wan t2i.
What resolution does Wan t2i output?
Public wan2.2 docs name 512–1440px a side, default 1024×1024. wan2.6-t2i names total pixels from 1280×1280 to 1440×1440. That is not a 4K still picker on this site.
Does Wan generate images from text?
Yes — on Alibaba Model Studio, as a PNG still. That is Wan t2i, not a one-shot still on ImgToVid, and not a Wan 3.0 clip.
How is this different from Wan video on this site?
The video Wan page runs Wan 3.0 (4–30s, 480p–1080p) and Wan 2.7 (2–15s). This image page is the stills API and is marked coming soon. Topaz enhances a photo; Uizard builds UI screens. This site opens none of those image desks.
Can I generate Wan images on ImgToVid?
No. The generator on this page runs GPT Image 2.5 Flare so you can draft a still. Wan t2i is marked coming soon. Video Wan 3.0 / 2.7 is a different page.
Can I use the results commercially?
Commercial use of anything you generate on ImgToVid depends on your plan. Check Pricing and our Terms before you publish, and make sure prompts and uploads do not infringe someone else’s rights.

Wan t2i is not the button on this page
You can still draft the still. The generator runs GPT Image 2.5 Flare, and the prompt goes with you into Create.
Draft in Create







