P-Video-Animate is now the fastest model for top-quality image-to-video motion transfer.
- $0.03/s at 720p and $0.06/s at 1080p β a fraction of typical motion-transfer pricing (~$0.07β$0.35/s at 720p in our benchmarks)
- 5.24 s generation time per second of output video at 720p β roughly 7Γ faster than typical motion-transfer alternatives in the same benchmarks
- Upload one still plus a driver video to preserve motion, timing, camera movement, and scene structure, with optional source audio and clips up to ~2 minutes at 720p
Ideal for UGC ads, gaming cinematics, film casting, and product demos when you already have a winning take and want a new hero still to follow it.
Try it in the playground: https://t.co/kUV7WzUXyd
Weβre launching with 70% discounted usage for the coming two days with our launch partners.
@eachlabs, https://t.co/YVg2KQrDmD
@replicate, https://t.co/By5Qk4ovrI
@runware, https://t.co/gqhDs5yASR
@scenario_gg, https://t.co/UQI8NF8jyR
@wavespeed_ai, https://t.co/HXrPVNHtRf
@wiroai, https://t.co/fmxGinBBiu
@TellersAI, https://t.co/DiBR9LIP16
Soon also on @togethercompute
Weβd love your feedback as you try it.
π Model docs & API examples: https://t.co/Tv5x6TXqlR
π API quickstart: https://t.co/fwgnfWSXIh
βοΈ OSS: https://t.co/8OGBDxHpzo
π https://t.co/DU9Bj08Q5R
Hell Yeah! @runware just published a practical guide for P-Video-Animate and wanted to share it with you!
Model features:
- $0.03/s at 720p and $0.06/s at 1080p
- ~5s generation time per second of output video
Their guide covers the request shape, the image/video pairing rule, optional prompt steering, and examples for portraits, cartoon characters, 3D characters, and mascots
Happy to hear your feedback!
https://t.co/TG4Wcfe9eA
MAI-Image-2.5 ranks #2 in the Image Edit Arena and advances the Pareto frontier.
That means: at its price tier, no model scores higher on Arena.
Congrats again to @MicrosoftAI on this release!
Cheap and Fast AI Animation of Motion For Still Images | @Scenario_gg x P-Video-Animate
See how Scenario's used our P-Video-Animate model for a cool launch video and generate a complete animation workflow yourself.
Fast, high-quality generation, and light on credits.
Try the model: https://t.co/UQI8NF8jyR
Check out all our models: https://t.co/xyWpgS08Mc
P-Video-Animate is now the fastest model for top-quality image-to-video motion transfer.
- $0.03/s at 720p and $0.06/s at 1080p β a fraction of typical motion-transfer pricing (~$0.07β$0.35/s at 720p in our benchmarks)
- 5.24 s generation time per second of output video at 720p β roughly 7Γ faster than typical motion-transfer alternatives in the same benchmarks
- Upload one still plus a driver video to preserve motion, timing, camera movement, and scene structure, with optional source audio and clips up to ~2 minutes at 720p
Ideal for UGC ads, gaming cinematics, film casting, and product demos when you already have a winning take and want a new hero still to follow it.
Try it in the playground: https://t.co/kUV7WzUXyd
Weβre launching with 70% discounted usage for the coming two days with our launch partners.
@eachlabs, https://t.co/YVg2KQrDmD
@replicate, https://t.co/By5Qk4ovrI
@runware, https://t.co/gqhDs5yASR
@scenario_gg, https://t.co/UQI8NF8jyR
@wavespeed_ai, https://t.co/HXrPVNHtRf
@wiroai, https://t.co/fmxGinBBiu
@TellersAI, https://t.co/DiBR9LIP16
Soon also on @togethercompute
Weβd love your feedback as you try it.
π Model docs & API examples: https://t.co/Tv5x6TXqlR
π API quickstart: https://t.co/fwgnfWSXIh
βοΈ OSS: https://t.co/8OGBDxHpzo
π https://t.co/DU9Bj08Q5R
Transfer Motion, Acting and Camera Movement with AI Editing | @wavespeed_ai x P-Video-Animate!
- $0.03/s at 720p and $0.06/s at 1080p
- ~5s generation time per second of output video
Find our models on their platform: https://t.co/i2VT8UhZmA
Check out all our model: https://t.co/xyWpgS08Mc
My idea-to-story pipeline is getting better thanks to Opus 4.8 and GPT-5.5. I basically work with them as a co-writer/director, and then you have image and video models getting better and cheaper as well, which creates these amazing compounding effects.
I was able to create this short for less than $10, and it would have been even cheaper if not for some iteration.
This was largely thanks to free image generation via Codex (GPT-Image-2), @PrunaAI's p-video and p-video-avatar models, and Gemini 3.1 TTS for the audio. Gemini is solid. It's definitely on the more expressive side, maybe even a little too expressive at times, but the final output came out alright. From there, the video models can take the audio directly and generate the final shots.
The mockumentary style actually works really well with p-video-avatar when it's just one person talking directly into the camera.
This story is called The Last Coder, and I literally just came up with it on a walk, then had it fleshed out in a few hours.
What a time to be alive!
Bring images to live with motion using agentic video edits!
Our newest model, P-Video-Animate, is now part of the family and live on @TellersAI: The agentic video editor!
Same Station F roots. Same belief: AI should be fast enough that creators stay in the creative loop.
Sub-second images. Video in seconds. Iterate without burning credits.
Read the full blog here: https://t.co/bTaoXS9m1n
Find all our models: https://t.co/xyWpgS08Mc
Try them in our playground: https://t.co/71Fjixbcry
Sign up for our API: https://t.co/ed2ONAKmvT
A few days ago I heard the official Swedish World Cup anthem and thought:
"I bet I can make a better one with AI."
Three days later that experiment somehow turned into a song, a music video, recurring characters, and an entire project called Mono Disco πΈπͺπ
Most of the time actually went into making the video.
Created with a mix of AI tools, music production, and internet culture.
Special shoutout to @PrunaAI β their p-video avatar was used for all the singing clips.
Pruna is currently the best at the cost/quality frontier and this ones going at a 70% discount for launch (0.009/sec for 720p). Still - I think this model can only do more simple movements like talking and simple movements (which is still great for the price).
Here I tried to restore and colorize the first known Kiss on film (in 1896!) but it couldn't quite follow the movements lol.
I think this could be a cool use case once we can reliably animate scenes. Take old movies and animate by scene:
-> use scene detection (ffmpeg, scenedetect) to get boundaries
-> slice up original video
-> extract first frame via ffmpeg
-> transform image to restored color version
-> animate the scene
-> rinse and repeat
-> concatenate all restored videos
P-Image-Upscale is the fastest and cheapest image upscaler in the world: supporting outputs up to 128 MP under 1 seconds.
A couple of weeks ago we released p-image-upscale, and it now works better than ever.
Itβs the fastest image upscaler in the world, supporting outputs up to 128 MP while keeping pricing simple and predictable:
- $0.005/image for 1β4 MP
- $0.01/image for 4β8 MP
- $0.02/image for 8β16 MP
- $0.04/image for 16β32 MP
- $0.06/image for 32β64 MP
- $0.12/image for 64β128 MP
That means you can go from low-res input to production-ready output with extreme speed, while preserving detail and keeping costs easy to understand.
Available on:
- @PrunaAI | https://t.co/a9KkyElI3O
- @eachlabs | https://t.co/xL8ao8LoGc
- @inference_sh | https://t.co/486fz7R1vW
- @replicate | https://t.co/Jq9PWIrMGs
- @runware | https://t.co/9FIzQv68zY
- @segmind_ai | https://t.co/zGZa042vQd
- @wavespeed_ai | https://t.co/LGPHC7gLHC
- @wiroai | https://t.co/QXI8AzFAGC
If youβre building workflows where image quality, price, latency, and scale all matter, p-image-upscale is built for you.