Control image composition with descriptive prompts. Specify subject placement, spatial relationships, and generate structured scenes.
Loading...
Use positional language in your prompt to describe where elements appear in the scene. Specify foreground, midground, and background layers, and use directional terms like left, right, center, top, and bottom to guide composition. The tool interprets spatial descriptions and generates images with structured layouts based on your text.
Input
A landscape split into three horizontal bands: foreground grass with flowers, middle section with a calm river, distant mountains under a cloudy sky
Expected output
A layered landscape composition with clear horizontal divisions, distinct foreground, midground, and background elements
Input
A large tree on the left side of the frame, a small cottage on the right, a winding path connecting them, birds in the upper right sky
Expected output
A balanced composition with specified subject placement, left-right visual flow, and sky details in the upper zone
Input
A coffee cup in the foreground centre, a laptop behind it to the right, a window with city view in the background, morning light
Expected output
A layered scene with clear foreground, midground, and background elements arranged by depth and position
Specify subject placement and spatial relationships through descriptive language in your prompt.
Describe how elements relate to each other in the frame to produce well-structured compositions.
Adjust positional or structural descriptions between generations to fine-tune the composition.
Describe the desired image.
Choose the available generation settings.
Generate, review, and download a suitable result.
Follow these guidelines to get the most out of the image generation tool.
Copy a structure, then adjust the subject, lighting, camera, and output details for your own result.
A mountain landscape with three clear layers: wildflowers and rocks in the foreground, a pine forest in the middle ground, snow-capped peaks in the far background, golden hour lighting
Explicitly names three depth layers and uses familiar spatial language to create a structured scene with clear foreground-to-background separation.
A medieval knight on the left third of the frame facing right, a dragon on the right third facing left, a narrow stone bridge between them in the center, dramatic sky above
Places two subjects using left-right positional terms and connects them with a central element, creating a balanced confrontation composition.
A long hallway with a door in the far background, a table with a vase in the middle distance, a chair in the near foreground on the right, warm light from windows on the left wall
Uses near, middle, and far depth cues combined with left-right placement to guide the viewer's eye through an interior space.
A flat lay view from directly above: a notebook in the top left, a coffee cup in the center, a smartphone in the bottom right, scattered pens around the edges, wooden table surface
Uses overhead perspective and clear positional terms for each object to create a controlled top-down composition.
A stone path entering from the bottom left corner and winding toward the upper right, a small house at the end of the path, trees flanking both sides, afternoon light from the upper left
Describes a diagonal compositional flow using corner references and directional language to create visual movement.
Match the workflow to the input you have and the result you need before opening the generator.
Input: Foreground-midground-background placement with specific left, right, center positioning for each object
Result: A structured product scene with clear depth and spatial relationships
Tool: Text to Image with detailed positional language and realistic style
Input: Layer-by-layer description using foreground, midground, background terms and directional placement
Result: An illustration with clear spatial structure and balanced element placement
Tool: Text to Image with illustrative style and compositional keywords
Input: Spatial descriptions using perspective cues, depth layers, and specific element positioning
Result: A scene with architectural depth and intentional composition
Tool: Text to Image with architectural or environment keywords
Power up your creative workflow with our AI-driven tools. Generate stunning videos, create images, and apply custom adjustments - our AI Video Generator and AI Image Generator offer a complete solution for all your creative needs.
Choose the credit package that works best for you.
No hidden fees • Cancel anytime • Unused credits roll over
Perfect for trying out AI creation.
Credits
200 credits / month
Billed monthly
First-time subscribers get 30% off their first month, then standard price
What's included
Perfect for light creators.
Credits
500 credits / month
Billed monthly
First-time subscribers get 30% off their first month, then standard price
What's included
Best value for creators
Credits
1,200 credits / month
Billed monthly
What's included
For video creators and power users.
Credits
5,000 credits / month
Billed monthly
What's included
Standard models only — upgrade to unlock premium models.
Credits
10 free credits on signup
Questions? Contact us at support@domer.io
Open the /text-to-image tool, describe your scene, and start creating visuals from your imagination.