Text to image3D & miniatures
The exact text-to-image prompt behind this picture, made with GPT Image 2.5 Sunburst.
Wide 16:9 landscape frame. A fully clothed Kenyan girl in a mint sweatshirt and cream dungarees builds a modeling dough city at a wooden craft table, pressing one cobalt bridge into place as coral buildings spill playfully beyond the table edge. Large simple shapes keep the scene readable. Hand sculpted stop motion aesthetic, broad afternoon window light, visible fingerprints and soft clay seams, absorbed joyful concentration, no logos, no text.
Prompts are kept in their original English to help reproduce the example. Copy one as it is, or adapt it for your project.
Opens GPT Image 2.5 Sunburst with this prompt and the settings below filled in.
135 tested GPT Image prompts →
The exact price shows before you generate.
broad afternoon window light.no text. Leave that in, or the model may add random lettering.Inspired by an idea from @Goodmanprotocol, collected in Evolink-AI/awesome-gpt-image-2-API-Prompts under CC0 1.0. PopNow wrote this prompt and made the example above.
Style prompt guide
A young Kenyan builder assembling miniature clay architecture creates a tactile diorama look when rendered with GPT Image 2.5 Sunburst. The combination of specific material cues and bold color choices guides the model to mimic handmade stop-motion sets rather than smooth digital plastic. Tactile imperfections like dough seams ground the miniature scale with believable depth and charm.
This visual style relies on tangible, physical modeling cues that simulate handcrafted plasticine materials captured under studio conditions.
Wide 16:9 landscape frame. A fully clothed Kenyan girl in a mint sweatshirtSets the composition bounds and introduces the primary subject before any action occurs. Altering this changes the focus and aspect framing of the workshop scene.
and cream dungarees builds a modeling dough city at a wooden craft table,Establishes the creative activity, character styling, and grounding tabletop surface. Omitting it risks losing the crafting context, turning the miniature buildings into a floating or ambiguous environment.
pressing one cobalt bridge into place as coral buildings spill playfully beyond the table edge.Directs the focal point to hands-on construction while designating a vivid two-tone color contrast. Removing it flattens the architectural depth and eliminates dynamic spillover beyond the tabletop.
Large simple shapes keep the scene readable. Hand sculpted stop motion aesthetic,Instructs the rendering engine to prioritize chunkiness over hyper-detailed realism, evoking stop-motion film animation. Removing this often leads the model toward generic, high-gloss 3D digital art.
broad afternoon window light, visible fingerprints and soft clay seams, absorbed joyful concentration, no logos, no text.Adds tactile realism through matte lighting and physical touch marks while suppressing unwanted brand marks. Without this phrase, surfaces look synthetically flawless and artificial.
Applies the handmade clay aesthetic to an animal subject while retaining identical lighting and material textures.
Wide 16:9 landscape frame. A playful golden retriever sculpted from modeling dough rests beside a miniature doghouse at a wooden craft table, nudging a bright teal ball with its snout as yellow tennis balls roll across the surface. Large simple shapes keep the scene readable. Hand sculpted stop motion aesthetic, broad afternoon window light, visible fingerprints and soft clay seams, no logos, no text.
Shifts the stop-motion style into a culinary still life using bold, recognizable clay breakfast shapes.
Wide 16:9 landscape frame. A tabletop breakfast feast of miniature modeling dough pancakes, a cobalt teapot, and coral fruit bowls arranged across a wooden craft table, with butter pats melting over rounded clay edges. Large simple shapes keep the scene readable. Hand sculpted stop motion aesthetic, broad afternoon window light, visible fingerprints and soft clay seams, no logos, no text.
Uses the same physical dough modeling style to construct a vehicle and miniature street environment.
Wide 16:9 landscape frame. A vintage delivery van sculpted from mint modeling dough navigates a curved cobblestone roadway bordered by chunky coral shopfronts on a wooden craft table. Large simple shapes keep the scene readable. Hand sculpted stop motion aesthetic, broad afternoon window light, visible fingerprints and soft clay seams, no logos, no text.
Run this image generation in text-to-image mode with quality set to high so fine material cues like fingerprint ridges and seam lines stay crisp. The 16:9 aspect ratio provides wide horizontal space across the craft table, letting the sprawling miniature town spread comfortably without clipping the edges. If you shift the subject to a single sculpture or a vertical tower, switch the aspect ratio to portrait while leaving the quality setting on high.
Prompt physical imperfections such as visible fingerprints, matte clay seams, and soft uneven edges. These tactile flaws signal to the model that the objects were physically rolled and pressed rather than digitally extruded.
Yes, swap cobalt and coral for any complementary pair such as mustard yellow and forest green. Limiting the architectural dough to two distinct tones keeps the composition organized and easy to read.
If buildings get cut off, reassert the wide 16:9 landscape frame at the beginning of the prompt and avoid terms like close-up or macro shot, which pull the virtual camera too tight to the table center.
Your photo
