Pastaio

Create something new.

Choose your inputs and check the cost before you start.

1

Choose what to create

2

Start with your idea

Choose what you want to work with.

Starting image

PNG or JPG · up to 10 MiB

Ending image · optional

PNG or JPG · up to 10 MiB

Explore ideas
Specific details help. You don’t need a perfect prompt.

Include the action and camera movement. Keep one clear idea per clip.

Kling 2.1 supports this creation method

Recent creations

Pick up where you left off.

Your creations will be kept here once you sign in

Set everything up now; you are asked to sign in when you press Create, and nothing here is lost.

Not sure what to make? See finished work and its prompts

Choose a model

Find the right tool for this task. Your compatible settings stay with you.

Image to video52 compatible modelsOnly models that support this mode are shown.
Seedance 2.5New
Pastaio x Seedance

Clips up to 30 seconds from a prompt, a picture, references with clips and sound, or carried on from a clip of your own, with native audio.

480p / 720p / 1080p / 4k4–30sStart + end frameSeed
≈340 credits
Veo 3.1 Lite
Pastaio x Google Veo

Veo 3.1 Lite: 8 second clips at 720p to 4K from text or a picture, with an end frame.

720p / 1080p / 4k8sStart + end frame
≈60 credits
Veo 3.1New
Pastaio x Google Veo

Google Veo 3.1: 8 second clips at 720p to 4K from text, a picture or up to three references, with a start and end frame.

720p / 1080p / 4k8sStart + end frame
≈500 credits
Veo 3.1 Fast
Pastaio x Google Veo

8 second clips at 720p to 4K from text or a picture, with an end frame.

720p / 1080p / 4k8sStart + end frame
≈120 credits
Seedance 2.0 Mini
Pastaio x Seedance

The smallest Seedance tier: 480p or 720p clips of 4 to 15 seconds, from text, a picture or references, with native audio.

480p / 720p4–15sAudio option
≈40 credits
Seedance 2.0
Pastaio x Seedance

Seedance 2.0: 720p to 4K clips of 4 to 15 seconds from text, a picture or references, with a start and end frame.

720p / 1080p / 4k4–15sStart + end frame
≈250 credits
Seedance 2.0 Fast
Pastaio x Seedance

720p to 4K clips from text, a picture or up to nine references, in six frame shapes.

720p / 1080p / 4k4–15sStart + end frame
≈150 credits
Seedance 2.0 VIP
Pastaio x Seedance

The Seedance 2.0 tier with the fullest input: references with clips and sound, start and end frames, 720p to 4K.

720p / 1080p / 4k4–15sStart + end frame
≈300 credits
Seedance 2.0 VIP Fast
Pastaio x Seedance

The VIP inputs — text, a picture or references with clips and sound — at 720p to 4K.

720p / 1080p / 4k4–15sStart + end frame
≈210 credits
Seedance 1.5 Pro
Pastaio x Seedance

Seedance 1.5 Pro: 480p to 1080p clips of 4 to 12 seconds from text or a picture, with native audio, an end frame and a still-camera option.

480p / 720p / 1080p4–12sAudio optionStart + end frameKeep the camera still
≈70 credits
Seedance 1.5 Pro Fast
Pastaio x Seedance

720p or 1080p clips of 4 to 12 seconds from text or a picture, with native audio and an end frame.

720p / 1080p4–12sAudio optionStart + end frameKeep the camera still
≈50 credits
Seedance 1.0 Pro Fast
Pastaio x Seedance

480p to 1080p clips of 2 to 12 seconds from text or a picture.

480p / 720p / 1080p2–12sKeep the camera still
≈12 credits
Seedance 1.0 Pro
Pastaio x Seedance

Seedance 1.0 Pro: 480p to 1080p clips from text or a picture, in six frame shapes.

480p / 720p / 1080p3–12s
≈35 credits
Kling 2.1Current
Pastaio x Kling

Kling 2.1: 5 or 10 second clips from text or a picture, with an end frame.

Model-defined size5–10sStart + end frame
≈240 credits
Kling 2.1 Standard
Pastaio x Kling

Kling 2.1's standard tier: 5 or 10 second clips from a picture, with an end frame.

Image to video only — this tier has no text-to-video endpoint.

Model-defined size5–10sStart + end frame
≈45 credits
Kling 2.1 Pro
Pastaio x Kling

Kling 2.1's Pro tier: 5 or 10 second clips from a picture, with an end frame.

Image to video only — this tier has no text-to-video endpoint.

Model-defined size5–10sStart + end frame
≈80 credits
Kling 2.5 Turbo Pro
Pastaio x Kling

Kling 2.5 Turbo's pro tier: 5 or 10 second clips from text or a picture.

Model-defined size5–10s
≈90 credits
Kling 2.5 Turbo Standard
Pastaio x Kling

Kling 2.5 Turbo's standard tier: 5 or 10 second clips from a still.

Image to video only — this tier has no text-to-video endpoint.

Model-defined size5–10s
≈55 credits
Kling 2.6 Pro
Pastaio x Kling

Kling 2.6 Pro: 5 or 10 second clips from text or a picture, with native audio.

Model-defined size5–10sAudio option
≈180 credits
Kling 3.0
Pastaio x Kling

Kling 3.0: 3 to 15 second clips from text or a picture, with an end frame and native audio.

Model-defined size3–15sAudio optionStart + end frame
≈140 credits
Kling 3.0 Pro
Pastaio x Kling

The Pro tier of Kling 3.0 — more detail in the same clear, calm motion, with native audio.

Model-defined size3–15sAudio optionStart + end frame
≈160 credits
Kling 3.0 4K
Pastaio x Kling

Kling 3.0 rendered at 4K — the same motion at four times the pixels.

The audio switch does not change the price at this tier.

Model-defined size3–15sAudio optionStart + end frame
≈400 credits
Kling 3.0 TurboNew
Pastaio x Kling

Kling 3.0's turbo tier: 3 to 15 second clips from text or a picture.

Model-defined size3–15s
≈110 credits
Kling 3.0 Turbo Pro
Pastaio x Kling

Kling 3.0 Turbo's Pro tier: 3 to 15 second clips from text or a picture.

Model-defined size3–15s
≈140 credits
Kling O1
Pastaio x Kling

Kling O1: 5 or 10 second clips from text or a picture, or 3 to 10 seconds from up to seven references, with an end frame.

Listed as “O3” on some other sites — this is that generation.

Model-defined size5–10sStart + end frame
≈140 credits
Kling O1 Standard
Pastaio x Kling

Kling O1's standard tier: 5 or 10 second clips from a picture or up to seven references, with an end frame.

Image and reference modes only — there is no text-to-video at this tier.

Model-defined size5–10sStart + end frame
≈100 credits
Gemini Omni 1.1 FlashNew
Pastaio x Gemini

Text-to-video with native audio and optional reference/character inputs.

720p / 1080p / 4kStart + end frameSeed
≈160 credits
Gemini Omni
Pastaio x Gemini

The full Omni tier — text or a first frame to video with native audio, up to 4K.

360p / 720p / 1080p / 4k4–10sSeed
≈310 credits
Wan 3.0New
Pastaio x Wan

Synchronized audio video with selectable resolution and duration.

480p / 720p / 1080p2–30sAudio optionStart + end frameSeedThink it through first
≈100 credits
Wan 3.0 Prime
Pastaio x Wan

Wan 3.0 Prime: 480p to 1080p clips up to 30 seconds from text, a picture or up to ten references with clips and sound, with native audio and an end frame.

480p / 720p / 1080p2–30sAudio optionStart + end frameSeedThink it through first
≈140 credits
Wan 2.7
Pastaio x Wan

Wan 2.7: 720p or 1080p clips from text, a picture or up to four references, with an end frame and an audio track of your own.

720p / 1080p2–15sStart + end frameAudio trackWhat to leave out
≈20 credits
Wan 2.6
Pastaio x Wan

Wan 2.6: 720p or 1080p clips of 5, 10 or 15 seconds from text or a picture, with an audio track of your own.

720p / 1080p5–15sAudio trackShots
≈130 credits
Wan 2.2
Pastaio x Wan

480p or 720p clips of 5 or 8 seconds from text or a picture, with an end frame and two detail levels.

480p / 720p5–8sStart + end frame
≈60 credits
LTX 2.0 Pro
Pastaio x LTX

Lightricks' LTX 2.0 Pro: 6, 8 or 10 second clips with native audio, from text or a picture.

Model-defined size6–10sAudio option
≈90 credits
LTX 2.0 Fast
Pastaio x LTX

6 to 20 second clips from text or a picture, with native audio.

Model-defined size6–20sAudio option
≈60 credits
LTX 2.3
Pastaio x LTX

LTX 2.3: 480p to 1080p clips from text or a picture; carries a clip on in Video tools.

480p / 720p / 1080p5–20sSeed
≈20 credits
LTX 2.5
Pastaio x LTX

LTX 2.5: 720p to 4K clips up to 20 seconds from text or a picture, with synchronized audio and an end frame.

720p / 1080p / 2k / 4k5–20sStart + end frameSeed
≈130 credits
MiniMax H3
Pastaio x MiniMax

MiniMax H3: 720p or 1080p clips of 5 to 15 seconds from text, a picture or references, with reference audio.

720p / 1080p5–15sStart + end frame
≈200 credits
MiniMax H3 Open
Pastaio x MiniMax

The open-weights H3: 480p or 768p clips of 5 to 15 seconds from text, a picture or references with clips and sound, with native stereo audio and an end frame.

480p / 768p5–15sStart + end frameSeed
≈50 credits
Hailuo 2.3
Pastaio x MiniMax

MiniMax's Hailuo 2.3: 6 or 10 second clips from text or a picture.

Model-defined size6–10s
≈70 credits
Hailuo 2.3 Pro
Pastaio x MiniMax

Hailuo 2.3 Pro: 768p or 1080p clips from text or a picture.

768p / 1080p
≈130 credits
Hailuo 2.3 Fast
Pastaio x MiniMax

6 or 10 second clips from a picture.

Image to video only — there is no fast tier for text to video.

Model-defined size6–10sFast rendering
≈50 credits
Sora 2
Pastaio x Sora

Sora 2: clips of 4 to 20 seconds from text or a picture, with synchronized audio.

Model-defined size4–20s
≈160 credits
Sora 2 Pro
Pastaio x Sora

Sora 2 Pro: 720p or 1080p clips of 4 to 20 seconds from text or a picture, with synchronized audio.

720p / 1080p4–20s
≈480 credits
Grok Imagine
Pastaio x Grok

Grok Imagine: 480p or 720p clips of 6 to 30 seconds from text, a picture or up to seven references, with ambient audio.

480p / 720p6–30sTone
≈30 credits
Grok Imagine 1.5
Pastaio x Grok

Image-to-video with multiple aspect ratios, up to 15 seconds.

Image-to-video only.

480p / 720p1–15s
≈130 credits
Happy Horse 1.0
Pastaio x Happy Horse

Expressive, stylized clips with vivid character motion.

720p / 1080p3–15s
≈180 credits
Happy Horse 1.1
Pastaio x Happy Horse

Refined Happy Horse tier with vivid character motion.

720p / 1080p3–15s
≈140 credits
Flux 3
Pastaio x Flux

Coherent motion and physically plausible scenes with ambient audio; continues a clip in Video tools.

720p / 1080p5–20sAudio optionStart + end frame
≈50 credits
LTX 2.3 Lipsync
Pastaio x LTX

A still portrait speaking a voice track, up to 1080p.

Takes a picture and an audio track; the face speaks the track.

480p / 720p / 1080pSeedVoice track
≈40 credits
InfiniteTalk Talking Portrait
Pastaio x InfiniteTalk

Animate a portrait to speak a voice track — an avatar or presenter from one photo.

Takes a picture and an audio track; the face speaks the track.

480p / 720pVoice track
≈40 credits
Wan 2.2 Speech to Video
Pastaio x Wan

A picture driven by speech — the subject talks along to the audio.

Takes a picture and an audio track; the subject speaks the track.

480p / 720pVoice track
≈40 credits
Only models that work with this way of starting are listed. The figures are rough guides; sign in to see your own price before anything starts.

Choose with confidence

Start with the job you need to do.

A model is the engine behind your result.

Different models support different inputs and controls. There is no single best model for every idea.

01

Choose the task first

Create from a prompt, animate an image, guide a scene with references, or transform an existing video. The list then shows only compatible models.

02

Check the controls you need

Look for your required duration, frame format, references and audio options. Settings are drawn from each model’s supported configuration.

03

Try a small, representative shot

Before committing to several creations, test the motion, visual style or voice that matters most. Review the quoted cost each time.

Keep creating

Choose a credit pack when you need more.

Available balance0 credits

You’ll be taken to a secure checkout. Credits are added to your balance once the payment is confirmed.

Creation details