Alibabas Tongyi Wanxiang Wan 2.7, jetzt auf OVOV. Ein Modell für Text-zu-Bild und Bildbearbeitung, mit herausragender chinesischer und zweisprachiger Typografie, bis zu 9 Referenzbildern und scharfer 2K-Ausgabe.
Modellnamen und Logos sind Marken ihrer jeweiligen Eigentümer. OVOV ist ein unabhängiges Produkt und steht in keiner Verbindung zu einem Modellanbieter, wird von keinem unterstützt oder gesponsert.
Built by Alibaba to be a versatile all-rounder — one model that generates from text and edits existing images, with typography that finally gets Chinese right.
Text-to-image and image-to-image live in the same model. Start from a prompt or restyle an existing photo — no switching tools.
Native-quality Chinese typography plus clean English — ideal for posters, packaging and social graphics for Chinese-speaking audiences.
Feed up to 9 references to keep a character, product or style consistent, or to guide precise edits.
Ink-wash, guochao, festival and traditional motifs render with a cultural fluency Western-trained models often miss.
Sharp 1K and 2K exports across common ratios — square, landscape, portrait — ready for web, print and social.
Wan 2.7 stays faithful to your composition, subject count and layout instructions — fewer surprises, more usable first drafts.
Wan 2.7 handles both paths — generate fresh or edit what you have.
Write a prompt in English or Chinese, or upload an image (plus up to 9 references) to edit.
The model composes your scene or applies your edit, rendering in 1K or 2K.
Export commercial-grade images with full usage rights — no watermark, no cleanup.
Wan 2.7 is the versatile pick for bilingual content, cultural aesthetics and everyday generate-or-edit work.
Festival posters, promotions and packaging with flawless Chinese set alongside English.
E-commerce visuals, banners and social cards across square, landscape and portrait ratios.
Restyle, extend or refine an existing image using up to 9 reference images for guidance.
Ink-wash landscapes, traditional illustration and cultural artwork with authentic detail.
Wan 2.7 reads natural language in English and Chinese — these techniques get the most from its text rendering and editing.
Best with clear subject and style cues
Quoted strings are rendered literally. Wan 2.7 is especially strong with Chinese characters.
Example
"A festival poster reading "新年快乐 · Happy New Year" in bold red and gold"
Provide up to 9 reference images to edit an existing image or lock a subject across a series.
Example
"Restyle the uploaded photo as a traditional ink-wash painting, keep the composition"
Wan 2.7 excels at Oriental and traditional styles — call them out for authentic results.
Example
"A guochao-style illustration of a phoenix, red and gold palette, intricate linework"
State how many subjects and where they sit. Wan 2.7 follows composition instructions reliably.
Example
"Two figures centered, mountains in the background, 16:9 landscape"
Request 2K for finished web and print work; 1K keeps drafts fast while you iterate.
Example
"2K e-commerce hero of a teapot on a wooden table, soft daylight"
Tell the model what to leave out — extra text, watermarks, clutter. Direct negatives work best.
Example
"Constraints: no extra words, no watermark, clean uncluttered background"