Wan 2.6 Image
Text to imagevellria-wan26-imagePrompt only, from a fixed list of output shapes that includes this family's widest.
Wan 2.6 Image is developed by Alibaba. Vellria provides access to the model; it does not own it. All trademarks belong to their respective owners.
Input
Form0 / 10000
Settings
Leave empty for a random value between 0 and 2147483647.
0 / 10000
Output
No generation yetCover art
6 credits
Your request will cost 6 credits.
Overview
Shape is a choice from a fixed list here rather than a number you type, and the two variants do not offer the same list, so it is worth picking the variant before picking the frame. Both take a seed and a negative prompt, and both leave the prompt optimiser switched off, so the wording you send is the wording that renders. Written that way, a prompt moves between the variants without being re-tuned.
Specifications
- Size: 1024×1024 (1:1)1280×720 (16:9)720×1280 (9:16)1280×960 (4:3)960×1280 (3:4)1280×1280 (1:1)1440×1440 (1:1)1920×1080 (16:9, FHD)1080×1920 (9:16, FHD)
Pricing
| Size | Credits |
|---|---|
| 1024×1024 (1:1) | 6 credits |
| 1280×720 (16:9) | 6 credits |
| 720×1280 (9:16) | 6 credits |
| 1280×960 (4:3) | 6 credits |
| 960×1280 (3:4) | 6 credits |
| 1280×1280 (1:1) | 6 credits |
| 1440×1440 (1:1) | 6 credits |
| 1920×1080 (16:9, FHD) | 6 credits |
| 1080×1920 (9:16, FHD) | 6 credits |
Variants in this family
What you are holding decides it. With only a description, the text variant is the one that will start, and it carries the widest shapes in this family — the edit variant does not offer them, so a frame that has to be that wide is drawn there. The edit variant will not begin without a picture, and it takes several of them at no extra charge, which makes it the cheaper place to work once you have material worth feeding back in.
| Variant | What it does | Credits |
|---|---|---|
| Wan 2.6 Image Edit | Edits from up to four reference images, and none of them adds to what the run costs. | 6 credits |