Refer to the uploaded image and transform the portrait ...
- Prompt
- Refer to the uploaded image and transform the portrait photo into a minimalist and trendy 3D cartoon character. Adopt a chibi full-body or half-body doll proportion, with a large head and small body. The character should be positioned in the center of the frame, standing upright, exuding a cold and lazy aura. The expression should be slightly world-weary, with drooping eyelids, relaxed gaze, straight mouth, round and plump face, small nose, and delicate, soft skin. The character should wear a light gray knitted cap and exaggerated black large headphones, with a small amount of bangs showing. The clothing should be a pure-colored loose knitted top with a simple design, natural draping, and unified and refreshing color scheme. The character design should have a trendy doll-like feel and an animated short film character vibe. The 3D modeling should be exquisite, with soft and delicate materials, clear knitting texture. The headphones should have a realistic plastic and frosted texture, with soft and even lighting. The background should be a high-saturation pure-color gradient background, with a clean and simple image, highlighting the main character. The overall visual should be cute, high-end, and fashionable, with a strong avatar and IP character feel. The output ratio is 1:1
- Size
- 1024 × 1536
- Model
- nano-banana
- Generation type
- text2img
- Created at
- 2026-03-19 15:14:34
How to use this deep-imager gallery example
This page is a moderated public-gallery still from the deep-imager AI image generator. It shows a real text to image result so you can study the prompt, model path, and framing before you recreate it with Make Same or start a fresh text to image / image to image run in the workspace.
What this still demonstrates
The creator’s prompt emphasizes: Refer to the uploaded image and transform the portrait photo into a minimalist and trendy 3D cartoon character. Adopt a chibi full-body or half-body doll proportion, with a large head and small body. The character should….
When you remix, keep the subject and lighting cues that already work, then change only one variable at a time (ratio, background, or style). That saves credits compared with rewriting the entire brief.
Recommended remix workflow
- Click Make Same to load the prompt into the deep-imager workspace.
- Lock the aspect ratio for your channel (9:16 Stories, 1:1 feed, 16:9 thumbs) before Generate.
- Run one text to image pass, then refine with image to image if you only need lighting or background edits.
- Keep client drafts Private. Enable Publicly visible only when the still is ready for gallery review.
Credits, policy, and reporting
Credit cost appears on the Generate button before you confirm. Failed runs follow the platform refund path. Public listings use automated safety checks plus human review; machine blocks are separate from gallery approval status. If this image breaks the rules, use Report this image or email support@flyingmob.com. Full UGC rules: Terms of Service.
Learn more: User guide How credits work Prompt checklist Make Same from gallery FAQ
Trademark notice: Third-party model or brand names on deep-imager describe optional access, style compatibility, or comparisons only. deep-imager is not affiliated with those trademark owners.