Prompting Guide
Your comprehensive guide to generating and editing images.
Core Features
- Text-to-Image: Generate high-quality images from simple or complex text descriptions.
- Image + Text-to-Image (Editing): Provide an image and use text prompts to add, remove, or modify elements, change the style, or adjust the color grading.
- Multi-Image to Image (Composition & Style Transfer): Use multiple input images to compose a new scene or transfer the style from one image to another.
- High-Fidelity Text Rendering: Accurately generate images that contain legible and well-placed text, ideal for logos, diagrams, and posters.
Prompts for Generating Images
The following strategies will help you create effective prompts to generate exactly the images you're looking for.
1. Photorealistic scenes
For realistic images, use photography terms. Mention camera angles, lens types, lighting, and fine details to guide the model toward a photorealistic result.
A photorealistic [shot type] of [subject], [action or expression], set in
[environment]. The scene is illuminated by [lighting description], creating
a [mood] atmosphere. Captured with a [camera/lens details], emphasizing
[key textures and details]. The image should be in a [aspect ratio] format.2. Stylized illustrations & stickers
To create stickers, icons, or assets, be explicit about the style and request a transparent background.
A [style] sticker of a [subject], featuring [key characteristics] and a
[color palette]. The design should have [line style] and [shading style].
The background must be transparent.3. Accurate text in images
Be clear about the text, the font style (descriptively), and the overall design.
Create a [image type] for [brand/concept] with the text "[text to render]"
in a [font style]. The design should be [style description], with a
[color scheme].4. Product mockups & commercial photography
Perfect for creating clean, professional product shots for e-commerce, advertising, or branding.
A high-resolution, studio-lit product photograph of a [product description]
on a [background surface/description]. The lighting is a [lighting setup,
e.g., three-point softbox setup] to [lighting purpose]. The camera angle is
a [angle type] to showcase [specific feature]. Ultra-realistic, with sharp
focus on [key detail]. [Aspect ratio].5. Minimalist & negative space design
Excellent for creating backgrounds for websites, presentations, or marketing materials where text will be overlaid.
A minimalist composition featuring a single [subject] positioned in the
[bottom-right/top-left/etc.] of the frame. The background is a vast, empty
[color] canvas, creating significant negative space. Soft, subtle lighting.
[Aspect ratio].6. Sequential art (Comic panel / Storyboard)
Builds on character consistency and scene description to create panels for visual storytelling.
A single comic book panel in a [art style] style. In the foreground,
[character description and action]. In the background, [setting details].
The panel has a [dialogue/caption box] with the text "[Text]". The lighting
creates a [mood] mood. [Aspect ratio].Prompts for Editing Images
These examples show how to provide images alongside your text prompts for editing, composition, and style transfer.
1. Adding and removing elements
Provide an image and describe your change. The model will match the original image's style, lighting, and perspective.
Using the provided image of [subject], please [add/remove/modify] [element]
to/from the scene. Ensure the change is [description of how the change should
integrate].2. Inpainting
Conversationally define a "mask" to edit a specific part of an image while leaving the rest untouched.
Using the provided image, change only the [specific element] to [new
element/description]. Keep everything else in the image exactly the same,
preserving the original style, lighting, and composition.3. Style transfer
Provide an image and ask the model to recreate its content in a different artistic style.
Transform the provided photograph of [subject] into the artistic style of [artist/art style]. Preserve the original composition but render it with [description of stylistic elements].Best Practices
To elevate your results from good to great, incorporate these professional strategies into your workflow.
- Be Hyper-Specific: The more detail you provide, the more control you have. Instead of "fantasy armor," describe it: "ornate elven plate armor, etched with silver leaf patterns, with a high collar and pauldrons shaped like falcon wings."
- Provide Context and Intent: Explain the purpose of the image. The model's understanding of context will influence the final output. For example, "Create a logo for a high-end, minimalist skincare brand" will yield better results than just "Create a logo."
- Iterate and Refine: Don't expect a perfect image on the first try. Use the conversational nature of the model to make small changes. Follow up with prompts like, "That's great, but can you make the lighting a bit warmer?" or "Keep everything the same, but change the character's expression to be more serious."
- Use Step-by-Step Instructions: For complex scenes with many elements, break your prompt into steps. "First, create a background of a serene, misty forest at dawn. Then, in the foreground, add a moss-covered ancient stone altar. Finally, place a single, glowing sword on top of the altar."
- Use "Semantic Negative Prompts": Instead of saying "no cars," describe the desired scene positively: "an empty, deserted street with no signs of traffic."
- Control the Camera: Use photographic and cinematic language to control the composition. Terms like wide-angle shot, macro shot, low-angle perspective.
Limitations
- For best performance, use the following languages: EN, es-MX, ja-JP, zh-CN, hi-IN.
- Image generation does not support audio or video inputs.
- The model won't always follow the exact number of image outputs that the user explicitly asked for.
- The model works best with up to 3 images as an input.
- When generating text for an image, Gemini works best if you first generate the text and then ask for an image with the text.
- Uploading images of children is not currently supported in EEA, CH, and UK
Frequently Asked Questions
What is imager.ink?
imager.ink turns your photos into stylized artwork using AI. Upload a picture, pick a style (e.g., “anime-inspired,” “retro 80s,” “cinematic portrait”), add a short description if you like, and download the result.
How does it work?
- Upload a photo (JPG/PNG/WebP).
- Choose a style or paste your own prompt.
- Hit Generate.
- Download your image once it’s ready. You’ll see a progress indicator in the app.
What kinds of photos work best?
Clear, well-lit images with the subject centered. Avoid heavy blurs, tiny faces, or extreme shadows. For portraits, a sharp head-and-shoulders shot gives the best results.
What file formats and sizes do you support?
JPG, PNG, and WebP are supported. Large images are fine, but if an upload fails, try under 10 MB or reduce the longest side to ~3000–4000 px.
What’s the output resolution?
We aim for a crisp, shareable resolution suitable for social, portfolios, and small prints. Exact size can vary by style; you’ll see the resolution on the download card.
Can you do passport/ID photos?
We can clean backgrounds and simulate “ID-style” framing, but official acceptance depends on your country’s rules. For actual passports/IDs, follow your issuing authority’s photo guidelines and use a certified photo service if required.
Are the styles “from” specific studios or brands?
No. We create original images inspired by broad aesthetics (e.g., “hand-painted anime vibe,” “Pixar-like 3D feel”). We’re not affiliated with or endorsed by any third-party brand, and we avoid direct trademark/character replication.
Who owns the images I upload and the results I generate?
- You own your uploads.
- You get rights to the outputs for personal and most commercial uses, as long as you respect applicable laws and third-party IP (e.g., don’t use someone else’s logo/character likeness commercially).
- If you used someone else’s photo, make sure you have permission.
Do you train on my images?
No, not by default. Your images are used to generate your result and to run the service (e.g., caching, moderation). We don’t use your content to train models unless you explicitly opt in to a future research/improvements setting.
How long do you keep my images?
Generated images are stored in your account for easy re-download. You can delete them anytime. We periodically clean older content to control storage costs and protect your privacy.
What content is not allowed?
We block:
- Sexual content involving minors or young-looking subjects
- Non-consensual intimate content
- Graphic violence and extremist propaganda
- Hateful or harassing content
- Illegal content and obvious IP violations (e.g., making exact copies of copyrighted characters or logos)
When in doubt, our moderation system may refuse a request.
Why did my image get rejected?
Likely moderation. Try a safer prompt, remove brand names/characters, or use neutral language. If you believe it’s a mistake, contact support with your request ID.
How much does it cost?
Pricing is shown in-app. You can buy image packs or subscriptions depending on what’s available in your region. Taxes may apply.
What payment methods do you accept?
Major cards and local options where available (processed by a secure payment provider). All payments are encrypted.
Do you offer refunds?
If a generation repeatedly fails or you’re charged without receiving a result, reach out within 7 days with your email and transaction ID. We’ll make it right.
How fast is generation?
Most requests finish quickly. Complex prompts or high traffic can take longer. You can safely leave the page open; you’ll see the result when it’s done.
Can I use the results commercially?
Generally yes, for original, non-infringing content. Avoid using protected logos, characters, or likenesses in ways that violate IP or publicity rights. If you’re producing merch at scale, do a quick legal check first.
Do you edit photos (background removal, color fixes, etc.)?
Yes, many styles include light cleanup. For precise edits (e.g., background to solid white, suit-and-tie look), choose an “ID-style” or “professional portrait” preset, or add it in the prompt.
Do you store my payment details?
We don’t store full card details. Payments are handled by a PCI-compliant provider.
What about my privacy?
We only collect what’s needed to run the service (e.g., account login, images you upload, generations you create). You can delete your content and request account deletion at any time via Settings or support.
How do I sign in?
Use “Continue with Google” (more options may be added later). Your library and purchases tie to this account.
Do I need an account?
Yes, to keep your generations, manage downloads, and prevent abuse. Guest support may appear in limited trials, but accounts are recommended.
My result looks weird. Any tips?
- Use a clearer source photo (sharp face, no sunglasses or heavy filters).
- Keep prompts short and specific.
- Try a different style or reduce conflicting instructions.
- Run it again—slight variations often help.
Can I re-download past images?
Yes—open your Library. If something’s missing (e.g., very old), it may have been cleaned up; try regenerating or contact support.
Can I delete my account and data?
Yes. Go to Settings → Delete Account. This removes your profile and associated content from our systems (some logs may be retained briefly for fraud/security).
Is there a mobile app?
The web app works well on mobile. A dedicated app may come later.
Accessibility
We aim for keyboard navigation and screen-reader friendly UI. If you hit any barriers, tell us and we’ll fix it.
Contact support
Email: support@imager.ink