Made for this idea
A new image guided by your references. The result may reinterpret fine details; keep the original photo for comparison. This is whole-image generation rather than a pixel-locked masked editor.
Image to image
Image to image
A new image guided by your references. The result may reinterpret fine details; keep the original photo for comparison. This is whole-image generation rather than a pixel-locked masked editor.
Image to image
Make the right first attempt
Prepare your starting material
Upload one to five JPG, PNG or WebP references, each up to 12 MB. Start with a clear face and add another angle only when it explains a marking or body feature.
What to check in the result
Say what should change and what should remain: for example, change the setting while keeping the ear shape, eye color and chest patch. Avoid combining an outfit, background, pose and lighting change in the first attempt.
From idea to saved work
1. Prepare the input
Upload one to five JPG, PNG or WebP references, each up to 12 MB. Start with a clear face and add another angle only when it explains a marking or body feature.
2. Direct one clear change
Say what should change and what should remain: for example, change the setting while keeping the ear shape, eye color and chest patch. Avoid combining an outfit, background, pose and lighting change in the first attempt.
3. Preview, compare and save
Check the quoted credits before submitting. When the work is ready, compare the face, edges and composition; for video, watch the beginning, middle and end. Download the accepted file from your library before its expiry date.
Image to image
A prompt you can actually use
This editable preset guides the model. Review the result before keeping it; a preset is not a guarantee of likeness, exact motion or flawless editing.
Edit the uploaded pet photograph. Soft watercolor pet portrait with visible paper texture. Preserve the pet’s recognizable face, coat markings and proportions. Do not add text or watermarks.Try the other starting point · Text to image →
Real inputs, recorded outputs
These are individual tests with licensed photographs or a written prompt. Compare the details before choosing a workflow; each result can differ.
A quiet portrait from a resting cat photo
The closed eyes and main coat markings remain recognizable. Fine markings, whiskers and the surface beneath the cat were redrawn; no wings or halos were added. This is a hypothetical memorial test, with no claim about the photographed animal’s life status.
Source photograph: Roy Tanck · CC0-1.0
Prompt and test details
C04 · 2026-10-13 · fal-ai/nano-banana-2/edit
Make a quiet, restrained commemorative portrait using this exact resting cat as the reference. Preserve the closed eyes, facial proportions, ears, whiskers and visible fur markings. Keep the same natural resting expression and age, with a soft warm neutral background and gentle natural light. No angel wings, halos, rainbow, heavenly scene, candles, flowers, dates, name, text or invented objects. This is a calm artistic portrait, not a restoration of a real event.
Images and videos are compressed for this page. The dimensions shown describe the downloadable original. Video previews use the delivered clip without changing its action or playback speed.
A watercolor portrait from a real reference
The seated pose, white blaze, dark saddle and white-tipped tail remain recognizable. The face and fur edges are redrawn, and woodland shapes remain despite the request for a plain background. Check these details before using the portrait.
Source photograph: Grzes1966 · CC0-1.0
Prompt and test details
R07 · 2026-10-14 · fal-ai/nano-banana-2/edit
Create a gentle watercolor portrait from this exact tricolor dog photo. Preserve the white blaze, black saddle, tan ears, white-tipped tail and visible seated pose. Keep the entire existing photo content in view. Use a clean pale cream paper background and soft sage accents. No additional animals, text, clothing, wings, halo, extra limbs or invented props.
Images and videos are compressed for this page. The dimensions shown describe the downloadable original. Video previews use the delivered clip without changing its action or playback speed.
A continuous background without inventing hidden anatomy
This retest removes the straight seam seen in an earlier attempt. Closed eyes, the blue collar and the visible right ear remain recognizable. Parts already cropped by the source stay at the frame edge. Fine fur details are still regenerated; this is not a pixel-locked edit.
Source photograph: Roy Tanck · CC0-1.0
Prompt and test details
R06 · 2026-10-14 · fal-ai/nano-banana-2/edit
Change the gray paving behind and below this resting cat to a seamless muted sage studio surface and backdrop. Preserve the same sleeping cat, its closed eyelids, face, white muzzle, tabby markings, blue collar, visible whiskers and original relaxed position. Keep the complete visible right ear inside the frame. The other ear and part of the body are already cut off by the original photograph: retain those natural frame-edge crops, do not invent their hidden parts. The visible fur must connect naturally to the edge of the picture, with no pasted rectangle or straight horizontal seam across the cat. No added objects, lettering, new pose, or opened eyes.
Images and videos are compressed for this page. The dimensions shown describe the downloadable original. Video previews use the delivered clip without changing its action or playback speed.
Downloads, access and privacy
Free previews carry a watermark: images up to 768 px on the long side and videos at 480p. They remain available for 14 days. Original access requires purchased credits when checkout is available; unlocked works are kept for 90 days. Check the actual dimensions and expiry on the completed work.
View pricing and access →Uploads and generated files belong to your private workspace. Generation providers process the material you submit. Sharing is a separate choice; upload only material you have permission to use.
Read the data-handling notice →Before you create
Which input should I choose?
Upload one to five JPG, PNG or WebP references, each up to 12 MB. Start with a clear face and add another angle only when it explains a marking or body feature.
What should I review before saving?
Say what should change and what should remain: for example, change the setting while keeping the ear shape, eye color and chest patch. Avoid combining an outfit, background, pose and lighting change in the first attempt.
Will it reproduce my pet exactly?
A reference image gives the model information to work from, but distinctive markings, proportions and expressions can change. Text-only creation invents a pet from your description. If exact documentary detail matters, retain the original photo alongside any AI interpretation.
Is a clean original included for free?
Free previews carry a watermark: images up to 768 px on the long side and videos at 480p. They remain available for 14 days. Original access requires purchased credits when checkout is available; unlocked works are kept for 90 days. Check the actual dimensions and expiry on the completed work.
Is this effect guaranteed?
This editable preset guides the model. Review the result before keeping it; a preset is not a guarantee of likeness, exact motion or flawless editing.