PetPortrait Bloom
Try it free

Image to video

Image to video

A five- or ten-second clip animated from the starting image. Choose gentle motion when preserving a familiar face matters. This does not recover an event that was never filmed.

This is an AI demo from a real generation run. It illustrates the input mode; it is not a result for every style or a customer photograph.

JPEG, PNG or WebP · up to 12 MB each · minimum 256 × 256

Be specific about the pet, appearance, scene and action. You can edit every preset.
For a new location or outfit, describe the still image here. We create it before animating; the quote includes both steps and the result includes both files. Leave empty to animate your original photo.

Image to video

Make the right first attempt

01

Made for this idea

A five- or ten-second clip animated from the starting image. Choose gentle motion when preserving a familiar face matters. This does not recover an event that was never filmed.

02

Prepare your starting material

Use one JPG, PNG or WebP image up to 12 MB. The starting pose should already show the parts that need to move. A close face crop cannot provide reliable information about hidden paws.

03

What to check in the result

Describe motion instead of repeating the entire image. Keep changes modest: blink once, turn slightly, hold the pose. For large actions, prepare a full-body starting frame with space around the animal.

From idea to saved work

  1. 1. Prepare the input

    Use one JPG, PNG or WebP image up to 12 MB. The starting pose should already show the parts that need to move. A close face crop cannot provide reliable information about hidden paws.

  2. 2. Direct one clear change

    Describe motion instead of repeating the entire image. Keep changes modest: blink once, turn slightly, hold the pose. For large actions, prepare a full-body starting frame with space around the animal.

  3. 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 video

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.

Animate the pet in the uploaded starting image. The pet gently blinks and breathes, with a still camera. Preserve its face, coat and body proportions. Smooth continuous movement, no captions or logos.
Try the other starting point · Text to video →

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 small blink with the full reference in view

Your starting point
Your starting point
The file you receive · 720 × 1280 · 5s

This sample closes and reopens its eyes, then slightly raises its head. The tall ears, green eyes and red harness remain recognizable. The light margins are visible in the result; exact blink counts and identity fidelity can vary.

Source photograph: Maxinjo; crop by YukiKoKo · CC0-1.0

Prompt and test details

R03 · 2026-10-14 · fal-ai/kling-video/v2.5-turbo/pro/image-to-video

Begin with the same open-eyed Savannah cat in the reference. The cat makes one slow, natural blink, fully reopening both eyes to the same original green eye color, then lifts its head just slightly. Preserve the exact tall ear shapes, muzzle, face proportions, asymmetric visible coat markings and red harness. Keep the body position, blue-sky background and camera almost still. Five calm seconds. No talking, yawning, eye-color change, exaggerated expressions, standing up, walking, new accessories, extra animals, text or scene cuts.

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.

From sitting to a few forward strides

Your starting point
Your starting point
The file you receive · 1280 × 720 · 5s

The dog stands and moves forward while the tail stays in view. The model invents the newly visible leg poses and turns the body away. This is a new motion interpretation; it does not preserve a recorded action. The reference margins remain visible.

Source photograph: Grzes1966 · CC0-1.0

Prompt and test details

R04 · 2026-10-14 · fal-ai/kling-video/v2.5-turbo/pro/image-to-video

Begin with the same seated tricolor dog from the reference. The dog calmly stands up on four paws, then takes two or three short jogging strides in the direction its body already faces. Use a stationary wide view with clear room ahead, keeping the entire visible body, both ears, all visible paws and the white-tipped tail inside the frame. Preserve the floppy ears, muzzle, white blaze and black saddle. Believable ground contact; no spins, no jumps, no camera tracking, no breed change, no clothing, no text. Five seconds.

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?

Use one JPG, PNG or WebP image up to 12 MB. The starting pose should already show the parts that need to move. A close face crop cannot provide reliable information about hidden paws.

What should I review before saving?

Describe motion instead of repeating the entire image. Keep changes modest: blink once, turn slightly, hold the pose. For large actions, prepare a full-body starting frame with space around the animal.

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.