Edit Image lets you make targeted, AI-driven changes to any image using natural language. Upload a reference image, describe the change you want—whether it’s adjusting lighting, swapping a background, modifying a character’s outfit, or adding new elements—and the AI applies your instructions while preserving the parts of the image you want to keep.
How to use Edit Image
- Open ImagineArt and select Edit Mode from the mode selector at the top.
- Upload the image you want to edit by clicking the + box or dragging your file in.
- Choose an editing model from the options below.
- Write a detailed prompt describing what you want to change.
- Set your aspect ratio and any other output settings.
- Click Create to generate the edited image.
Be specific in your edit prompt. Instead of “change the background,” try “replace the background with a sun-drenched Tuscan vineyard at golden hour.” Precision helps the AI understand exactly what you want.
Editing models
Each model has different strengths. Choose the one that fits your editing goal.
Flux Kontext
Nano Banana
ChatGPT Image
Imagine You
Runway Reference
Upscale
Best for: Precise local edits, character consistency, and context-aware modifications.Flux Kontext is a multimodal AI model developed by Black Forest Labs that combines text and visual context to make highly targeted edits. You can upload a photo and instruct it to change specific elements—clothes, background, colors—while keeping the rest of the image intact.Key capabilities:
- Instruction-based editing — Make precise changes to specific areas without disturbing the overall composition.
- Character consistency — Maintain the same character’s appearance across different edits or scenes.
- In-context generation — Use both text and reference images together for nuanced results.
- Fast iteration — Designed for real-time creative workflows with quick generation speeds.
How to use Flux Kontext:
- Select Edit Mode and choose Flux Kontext as your model.
- Upload up to 4 reference images to guide the AI.
- Write a prompt specifying which elements to change (e.g., “change the jacket to a red leather jacket, keep everything else the same”).
- Set your aspect ratio and image count.
- Click Create.
Example prompt: "Change the background to a snowy mountain landscape. Keep the character and lighting exactly as is." Best for: Complex natural language instructions, scene adjustments, and perspective changes.Nano Banana, developed by Google, understands complex editing instructions similar to how a conversational AI processes language. It excels at interpreting multi-part instructions and making nuanced adjustments to scenes, angles, and object placement.Key capabilities:
- Understands complex, multi-step editing instructions in plain language
- Adjusts scene angles, perspectives, and spatial relationships
- Adds, removes, or repositions objects based on descriptions
- Produces high-fidelity textures and stylized outputs
How to use Nano Banana:
- Select Edit Mode and choose Nano Banana as your model.
- Upload up to 3 reference images.
- Write your editing prompt, describing what you want to change or add.
- Click Create.
Example prompt: "Shift the camera angle to a low-angle shot looking up at the subject. Add dramatic storm clouds to the sky." Best for: Multi-element compositions, detailed scene generation, and images with embedded text.ChatGPT Image by OpenAI excels at prompt accuracy and complex scene construction. It is particularly strong when you need multiple distinct elements to coexist in a single image or when your image needs to include readable, correctly spelled text.Key capabilities:
- Highly prompt-accurate: follows detailed, multi-part instructions closely
- Strong at generating complex scenes with many interacting elements
- Best-in-class text rendering inside images
- Character and object design from detailed descriptions
How to use ChatGPT Image:
- Select Edit Mode and choose ChatGPT as your model.
- Upload up to 3 reference images.
- Write your detailed editing or generation prompt.
- Click Create.
Example prompt: "Add a chalk-board sign in the background that reads 'Grand Opening' in bold script. Keep the storefront and lighting unchanged." Best for: Character consistency across multiple scenes, poses, and styles.Imagine You is a specialized character consistency model. Upload a single reference photo of a person or character, and it generates variations of that same character in different poses, outfits, environments, and artistic styles—while preserving their core visual identity.Key capabilities:
- One-shot character consistency from a single reference photo
- Generates variations across styles (photorealistic, cartoon, fantasy, etc.)
- Explore different poses, clothing, and settings while maintaining likeness
- Select presets or guide output through the prompt box
How to use Imagine You:
- Select Edit Mode and choose Imagine You as your model.
- Upload a clear reference photo of your character.
- Select a style preset or write a custom prompt to describe the variation you want.
- Set aspect ratio and image count, then click Create.
Example prompt: "Same character, wearing a futuristic silver spacesuit, standing on a Martian landscape, dramatic cinematic lighting." Best for: Extracting and applying styles, textures, or visual characteristics from reference images.Runway Reference lets you extract specific visual characteristics—textures, colors, layouts, and styles—from one or more reference images and apply them to new generations. It is ideal for branding projects, series of concept art, or any work that requires visual consistency across multiple outputs.Key capabilities:
- Maintains visual consistency across multiple generated images
- Extracts and applies color palettes, textures, and compositional styles
- Accepts up to 3 reference images as style sources
- Works for both stylistic and structural consistency
How to use Runway Reference:
- Select Edit Mode and choose Runway Reference as your model.
- Upload up to 3 reference images that embody the characteristics you want to preserve.
- Write a prompt describing the new content or scene.
- Click Create.
Example prompt: "A product shot of a glass perfume bottle, using the same warm amber tones, soft lighting, and clean white background from the reference images." Best for: Increasing image resolution and sharpness without re-generating.Upscale is an AI-powered resolution enhancement tool. It takes an existing image and increases its resolution, either faithfully preserving all original details or creatively enhancing them with added depth and richness.Upscale options:
- Subtle — Increases resolution while retaining all original details and characteristics. Use this when you want the image to look identical, just larger and sharper.
- Creative — Upscales the image and adds creative details to enrich the composition. Use this to breathe new life into an image while boosting its resolution.
Supported upscale engines and costs:| Engine | Scales | Credits |
|---|
| Topaz | 2×, 4× | 2×: 169 / 4×: 338 |
| Magnific Precision v2 | 2×, 4×, 8×, 16× | 2×: 130 / 4×: 260 / 8×: 520 / 16×: 1,040 |
- Select Edit Mode and choose Upscale as your tool.
- Upload the image you want to upscale.
- Choose Subtle or Creative, select your scale factor, and click Create.
Upscale credit costs may vary depending on the size of the input image and the chosen output scale. The Image mode tooltip shows the exact cost before you generate.
Supported models summary
| Model | Uploaded references | Primary strength |
|---|
| Flux Kontext Max | Up to 4 | Precise local edits, character consistency |
| Nano Banana | Up to 3 | Complex natural language instructions |
| ChatGPT Image | Up to 3 | Multi-element scenes, embedded text |
| Imagine You | 1 | Character variations from a single photo |
| Runway Reference | Up to 3 | Cross-image style and visual consistency |
| Seedream v4 Edit | 1 | Dream-like, artistic edits with creative flair |
| Qwen Edit | 1 | Intuitive edits with style transfer and fine-tuning |
