Pruna AI

P-Video-Avatar is now the fastest model for top-quality and diverse avatar generation. - It costs 0.025$ per second of video, making it up 6× cheaper than similar avatar tools - It takes 1.83s generation time per second of video, making it up to 18x faster than similar avatar tools. - It offers full-body control, integrated audio support in 20+ languages, and is long-form video-ready for up to 3-minute consecutive clips. We are launching with free usage until Sunday 23:59 CET at @replicate, @WiroAI, @inference_sh, @Runware, @Scenario_gg And with general availability at: @deepinfra, @Eachlabs Try it now: …-playground-production.up.railway.app 📚 API & quickstart for Pruna API: docs.api.pruna.ai/guides/quickst… ⭐️ Star our OSS: github.com/PrunaAI/pruna 🌐 Website: pruna.ai

@fabdreamai Do you feel like it happens even when the starting image is looking directly at the camera?

@PrunaAI I mean the eyes, they lose focus and stop looking straight at the camera, sometimes going slightly off-axis mid-sentence. It breaks the illusion instantly, and even explicit prompts like 'look directly at the camera' don't fix it. You can actually see it in your own demo.

We launched P-Video-Avatar last week, and we've loved the community's responses, which have confirmed our claim: it is the fastest and cheapest way to generate top-quality, diverse AI avatars! - It costs 0.025$ per second of video, making it up to 6× cheaper than similar avatar tools - It takes 1.83s generation time per second of video, making it up to 18x faster than similar avatar tools. - It offers full-body control, integrated audio support in 20+ languages, and is long-form video-ready for up to 3-minute consecutive clips. Thank you to our launch partners: @replicate, @WiroAI, @inference_sh, @Runware, @Scenario_gg , @deepinfra, @Eachlabs Try it now: …-playground-production.up.railway.app 📚 API & quickstart for Pruna API: docs.api.pruna.ai/guides/quickst… ⭐️ Star our OSS: github.com/PrunaAI/pruna 🌐 Website: pruna.ai

@fabdreamai Can you explain more what you mean by drifting? It would be valuable for us to improve the model!

@PrunaAI Tried it , the pricing is solid but the eyes keep drifting no matter how tight the prompt is. Still a gap to close before it competes with HeyGen on quality.

@replicate @WiroAI @inference_sh @runware @Scenario_gg @DeepInfra @Eachlabs eachlabs.ai/pruna/p-video/…

@replicate @WiroAI @inference_sh @runware @Scenario_gg @deepinfra deepinfra.com/PrunaAI/p-vide…

lol Just realized @PrunaAI free deadline for p-avatar was in CET. 😆 oh well its still pretty cheap and this is worth it

Free P-Video-Avatar usage until Sunday 23:59 CET at @replicate: replicate.com/prunaai/p-vide…

@mattiasOfSweden @DeepInfra P-video does support last_frame! replicate.com/prunaai/p-video

@PrunaAI @DeepInfra Last time I checked I couldn’t see end frame support. Have I missed anything?

P-Video-Avatar is now the fastest model for top-quality and diverse avatar generation. - It costs 0.025$ per second of video, making it up 6× cheaper than similar avatar tools - It takes 1.83s generation time per second of video, making it up to 18x faster than similar avatar tools. - It offers full-body control, integrated audio support in 20+ languages, and is long-form video-ready for up to 3-minute consecutive clips. We are launching with free usage until Sunday 23:59 CET at @replicate, @WiroAI, @inference_sh, @Runware, @Scenario_gg And with general availability at: @deepinfra, @Eachlabs Try it now: …-playground-production.up.railway.app 📚 API & quickstart for Pruna API: docs.api.pruna.ai/guides/quickst… ⭐️ Star our OSS: github.com/PrunaAI/pruna 🌐 Website: pruna.ai

@mattiasOfSweden @DeepInfra We also offer that and it is called P-Video 🫶💜

@PrunaAI @DeepInfra Just tested it and… wow. It’s amazing. Exactly what I need right now. On my wish list. A really fast video model with support for first and last frame.

@zeng_wt Make those purple creations speak

@PrunaAI Love this model!!

@ashen_one @replicate You can provide your own audio as input!

@replicate @PrunaAI visuals are great but audio is bad what's this powered by :0

P-video-avatar by @PrunaAI is live - Built-in TTS, 20+ languages + voice selection - Dynamic backgrounds + body/camera control - Up to 3-minute generations - 1080p support, $0.025/sec - Cinematic-quality avatars Free all weekend ↓

@JayBisen473370 @runware Awesome! Let us know what you create💜

@runware That's awesome! Excited to see how creative we can get with those avatars. Free until Sunday? Perfect time to try it out!

P-Video-Avatar from Pruna AI is now on Runware on D0! 🎬 - 30 voices, multiple languages, 720p or 1080p - full-minute generation - avatar movement, background and tone controllable through prompting for free on runware until Sunday 23:59 CET

@aaliya_va @runware Show us what you create!

@runware Will try it.

@adithatipalli @replicate @PrometheanAIX Thank you for the kind words!

@replicate @PrometheanAIX @PrunaAI this is a Banger. the quality of it is precisely as humanely possible

@seergioo_gil @replicate Thanks a lot for the support!

@PrunaAI @replicate this is insane