
AI generator
Text to Image: Turning a Description into a Picture
Generating from text alone means the words carry everything, so the way you write matters. This page covers how models read a prompt, what order to put details in, and how to fix results that miss the point.
Made with OpenDream
See more in the galleryHow it works
- 01
Lead with the subject
Put the main subject and what it is doing in the first few words. Models weigh early words more heavily, so 'an old fisherman mending a net' should come before lighting or style.
- 02
Add setting, light and framing
Follow with where it happens, the light source and the viewpoint: 'on a pier at dawn, low sun from behind, close-up at eye level'.
- 03
End with style, then iterate
Close with medium and mood, generate, and change one phrase at a time. If the wrong element is emphasized, move it earlier or describe it more concretely.
Why create text to image with OpenDream
Plain language prompts
No special syntax or weights are required. Full sentences work, and so do comma-separated phrases; use whichever helps you think clearly.
Models that read words differently
Some models follow long, detailed instructions closely while others interpret loosely and add their own flair. Smart mode chooses for you, and switching models shows how the same words are read.
Legible words inside the picture
When the image needs a readable sign, label or headline, Ideogram V3 and GPT Image 2 are the strongest options for typography.
Prompt examples to learn from
Browse prompt examples by category and use them as a starting point for your own wording.
How to structure a prompt so the model follows it
A dependable structure is subject, action, setting, light, framing, style. The model does not enforce it, but it mirrors how people describe pictures and stops you from forgetting a layer. 'A girl on a bicycle' becomes 'a teenage girl riding a bicycle with a basket of oranges, cobbled hill street, late afternoon backlight, wide shot from street level, warm film photograph'. Every added phrase removes a guess.
Be concrete about what matters and quiet about the rest. If the bicycle's color is important, state it; if not, leave it out rather than padding with 'beautiful, amazing, highly detailed'. Stacked quality words dilute the prompt and rarely improve results on current models.
Describe what you want rather than what you do not want. 'An empty beach' tends to beat 'a beach with no people', because mentioning people can pull them into the frame. When something keeps appearing, replace it with a positive description of what should fill that space.
For lettering, put the exact words in quotation marks and keep them short, ideally under six words. Say where the text sits and how it looks: 'the words "Night Market" in hand-painted red lettering on a wooden sign above the stall'. Proofread every result, since even strong typography models occasionally swap a letter.
Prompt examples
Full-structure example
A teenage girl riding a bicycle with a basket of oranges down a cobbled hill street, late afternoon backlight, long shadows, wide shot from street level, warm color film photograph with fine grain
It runs through subject, action, setting, light, framing and style in order, so nothing important is left to chance.
Try this promptSign with exact wording
A night market food stall lit by string bulbs, steam rising from woks, the words "Night Market" in hand-painted red lettering on a wooden sign above the stall, shallow depth of field, humid atmosphere
Short quoted text with a described lettering style and position gives typography models the best chance of spelling it right.
Try this promptEmptiness described positively
An empty winter beach at first light, smooth wet sand reflecting a pale pink sky, a single line of footprints leading to the waterline, quiet minimal composition, soft haze over the sea
Instead of saying 'no people', the footprints imply absence and give the eye a path through the frame.
Try this promptSingle-object study
A cracked ceramic teapot repaired with gold seams, sitting on a linen cloth, single window light from the left, dark background, still-life photograph with rich texture and gentle falloff
One object, one light and a plain background is the simplest way to see how a model handles material and texture.
Try this promptIllustrated scene
Storybook illustration of a hedgehog postman delivering letters through a snowy village at dusk, lantern glow in cottage windows, soft gouache textures, gentle rounded shapes, cozy and calm
Naming the medium (gouache) and the shape language (rounded) steers the look without leaning on an artist's name.
Try this prompt
Start from a template
Frequently asked questions
- How long should a prompt be?
- Long enough to cover what matters. One to three sentences handles most images. Longer prompts can work on models that follow detail closely, but the important elements should still come first.
- Why does the model ignore part of my prompt?
- Usually the missing detail was late in the prompt, vague, or in conflict with something else. Move it earlier, make it concrete, or remove the competing instruction.
- Can I include a title or words in the picture?
- Yes. Quote the exact text and keep it short. Ideogram V3 and GPT Image 2 handle lettering best; check the spelling in every result.
- Do I need negative prompts?
- Rarely. Describing the scene you want in positive terms is more reliable than listing things to avoid.
Keep exploring
Ready to create?
Pick a plan and you only spend credits on images you actually receive.
Start creating




