Describe the image you imagine—no reference photo required. Choose an aspect ratio and resolution, then generate in your workspace.
Explore images created by our team, from a theater portrait and a lamp concept to a lighthouse and an imagined observatory. Notice how subject, materials, setting and light can define a visual direction.
Start with the subject: a ginger cat. Add an action and location, such as sitting beside a window, then describe warm afternoon light and a quiet mood. Each detail gives your written description a clearer direction. If the subject is unclear in the result, revise its defining features before adding more background detail.
For a product concept, describe its shape, material, finish and placement. A matte insulated bottle on a stone surface communicates more than a stylish product. Add the background and lighting you need. Text-to-image generation can explore a concept, but it is not a substitute for checking the exact design, labels and details of a real product.
Separate who is in the picture from how it should look. Describe expression, clothing and surroundings, then specify a photographic or illustrated style. For a seaside portrait, decide between soft daylight and dramatic evening light. If the mood is wrong, change the light or color palette rather than adding vague words like beautiful or professional.
You can describe a cafe through its terracotta walls, teal seating, curved architecture and warm window light without uploading a photo. If an existing image matters to your request, you can optionally add one JPEG, PNG or WebP reference with an original file smaller than 50 MiB, and explain which features should guide the result. Explore AI image to image generation for a reference-led workflow, or the AI image generator for an overview of both input options.
Describe the camera angle, distance and subject position: a cyclist in the foreground, mountains in the distance and open space beside the subject. A wider view shows more surroundings; a close-up emphasizes detail. Select the aspect ratio in settings. If the composition misses your intention, revise the framing and placement rather than only increasing resolution.
Build your description around these four elements. Put the essential requirements first; you do not need to fill every category or write a long prompt. Review the result, then change one detail at a time to understand what helps.
Identify the subject, its number, key features and action. When the result misses what matters, make those details more explicit instead of adding unrelated adjectives.One ginger cat sitting and looking outside
Describe the location and how the subject fits into it. Name a few useful surfaces or background elements. If the result is crowded, simplify the setting and specify an uncluttered background.A wooden windowsill, with linen curtains and a simple background
Specify the light source, direction, color palette and visual style. If the atmosphere is wrong, change a concrete choice such as soft window light versus strong shadows rather than asking for a better image.Warm afternoon window light, a quiet mood, natural photographic style
Describe the viewpoint, framing, subject position and any empty space. If the framing is wrong, revise those instructions and check the selected aspect ratio. Set resolution and aspect ratio in the controls, not just in your prompt.An eye-level medium shot, with the cat on the right and empty space on the left
One ginger cat sitting on a wooden windowsill, looking outside. Linen curtains and a simple background. Warm afternoon window light, a quiet mood, natural photographic style. An eye-level medium shot, with the cat on the right and empty space on the left. This teaching example shows how to combine the four elements; it is not a promise to reproduce the displayed image.
Start with a written description, set your image format, then generate and review the result in your workspace.
Describe the subject, action, setting and visual style in up to 1,000 Unicode characters. A text prompt is enough; no reference photo is required.
Choose the aspect ratio and resolution independently. Each task costs 3 credits at 1K, 4 credits at 2K or 5 credits at Up to 4K.
Continue to your workspace and sign in to generate. Review your image, download the PNG or revise your description and generate again.
Yes. Enter a written description without uploading a photo. The AI text to image generator creates a new image from your prompt. One reference image is optional. If selected, your browser automatically compresses it before submission to a static WebP smaller than 20,000 bytes (20 KB, decimal), preserving the full frame and aspect ratio without cropping. Fine text and textures may become blurred.
State the important subject details, setting and composition clearly. Remove conflicting instructions and use concrete lighting or style descriptions. After reviewing a result, adjust one element at a time. AI-generated images may not follow every detail exactly, and generating again can produce a different result.
Choose 1K, 2K or Up to 4K resolution settings and an aspect ratio of 1:1, 16:9, 9:16, 3:2 or 2:3. All five ratios are available at every resolution tier. Aspect ratio sets the shape; resolution sets the requested pixel dimensions independently. The highest pixel dimensions depend on the aspect ratio. Each task generates one image, downloadable as a PNG when complete.
Yes. New accounts receive 50 free credits, valid for 30 days. A task costs 3 credits at 1K, 4 credits at 2K or 5 credits at Up to 4K. This is a signup allowance, not an unlimited or daily grant. See pricing and credit options for further use.
Yes. Both free and paying users may use generated images commercially. You must have the necessary rights to any reference material you upload. See the Terms of Service for the applicable conditions.
Your uploads and generated images are private by default in your account. Your prompts, uploads and outputs are not used to train AI models. See the Privacy Policy for processing and storage details.
