Bertrand Charpentier (@Bertrand_Charp) - Twitter Profile

Naka-pin na Tweet

Bertrand Charpentier@Bertrand_Charp·5 Nis

Happy to announce NatPN at #ICLR2022 (Spotlight) ! - It predicts uncertainty for many supervised tasks like classification & regression. - It guarantees high uncertainty for far OOD. - It only needs one forward pass at testing time. - It does not need OOD data for training.

English

2

44

199

0

Bertrand Charpentier@Bertrand_Charp·7h

P-image-upscale is now the fastest upscaler model. - It takes less than a second for upscaling. - It can be combined after any image model.

Pruna AI@PrunaAI

New from Pruna AI: The P-Image-Upscale endpoint boosts image resolution with sharper details in under a second. Get up to 8 MP output for just $0.005 per call. Get more info at: pruna.ai/p-image-upscale Sign up for the Pruna API: dashboard.pruna.ai Try it directly on @replicate: replicate.com/deployments/pr… Quick, affordable image upscaling for your apps. ✉️ Contact: pruna.ai/contact ⭐️ Star our OSS: github.com/PrunaAI/pruna 📚 API & quickstart: docs.api.pruna.ai/guides/quickst…

English

1

0

4

294

Bertrand Charpentier nag-retweet

Pruna AI@PrunaAI·2d

🎉 Pruna OSS is turning 1! To mark this milestone, we're launching the First Prune initiative. Get involved by contributing to open issues at our GitHub repo and earn Pruna Inference API credits. Here’s how: • Pick an open issue labelled "first-prune" and assign it to you • Submit your PR and mark it ready for review by April 30 • Find out more in the PR template when you open a PR Each merged PR scores 30 credits. Let’s build something great together! Find your issue 👇 github.com/PrunaAI/pruna/… ⭐️ Star our OSS: github.com/PrunaAI/pruna 🗓️ Follow our events: luma.com/pruna-ai Check out open issues here: github.com/PrunaAI/pruna/…

English

0

10

22

637

Bertrand Charpentier@Bertrand_Charp·3d

Proud to support the Resilient AI Challenge organized by France🇫🇷, India🇮🇳, and @UNESCO🌍 As part of the challenge, work on real-world models from @MistralAI, @Google, and @SarvamAI, making them more efficient without sacrificing quality! Join here👉 sustainableaicoalition.org/resilient-ai-c… The end goal is to advance open progress toward accessible and sustainable AI — at the core of @PrunaAI mission! In collaboration with @huggingface, @MistralAI, @SarvamAI, @Capgemini🙌

English

1

2

4

68

Bertrand Charpentier@Bertrand_Charp·6d

P-Image, P-Image-Edit, and P-video are the fastest models in their categories according to @Designarena 🤪 - Generate one image in ~1s - Edit one image in ~1s - Generate one video in ~5s (Recently udpated!) Try the @PrunaAI API here: dashboard.pruna.ai/login :)

English

0

1

5

133

Bertrand Charpentier@Bertrand_Charp·6d

P-video is x2 faster: 5s generation speed for a 5s video. Other video models usually take around minute.

Pruna AI@PrunaAI

⚡️P-video is faster now. A 720p 5-second video takes only 5 seconds at 0.02$ per second! Sign up for our API now: dashboard.pruna.ai/login Try our Endpoint Guides: docs.pruna.ai/en/stable/docs… Star our OSS: github.com/PrunaAI/pruna

English

0

3

113

Bertrand Charpentier nag-retweet

Pruna AI@PrunaAI·26 Mar

🎬🔚 P-video now has last frame support! This allows you to have fine-grained control over all your generated videos and to chain scenes together without difficulty. Sign up for our API: dashboard.pruna.ai/login Try our endpoint guides: docs.pruna.ai/en/stable/docs… Star our OSS: github.com/PrunaAI/pruna

English

1

4

18

379

Bertrand Charpentier nag-retweet

Pruna AI@PrunaAI·12 Mar

P-video just got an update! Same price, same speed, better ... 👇 - Better character consistency - Better sound + audio in draft mode - Better quality overall 🎠 Try our free demos: dub.sh/sEN7i8c 💜 Sign up for our events: dub.sh/BDmCNBx 🎉 Find all of our models: dub.sh/OP90LS6 ⭐️ Star our OSS GitHub: dub.sh/ZA6N6YS

English

3

9

45

4.1K

Bertrand Charpentier nag-retweet

inference.sh@inference_sh·12 Mar

all @PrunaAI models are now available: app.inference.sh/apps/pruna Pruna optimizes AI models for speed without quality loss. Now available: • P-Image & P-Video - their flagship fast generation • Optimized FLUX, WAN, Qwen, Z-Image

English

4

7

19

2.1K

Bertrand Charpentier@Bertrand_Charp·10 Mar

Happy to release SOTA compression algorithms in the @PrunaAI open-source package (and you can even combine them together) ;) - Package: github.com/PrunaAI/pruna - Documentation: github.com/PrunaAI/pruna

Pruna AI@PrunaAI

🚀 Release 0.3.2: We’ve added some new algorithms to Pruna OSS! - Recoverers - Compilers - Decoders - And many, many more… 📚 Check out the docs: dub.sh/Ht2ryVg ⭐️ Star our OSS GitHub: dub.sh/wqToxlX 💜 Sign up for our events: dub.sh/nRlyHuU

English

0

7

275

Bertrand Charpentier nag-retweet

Pruna AI@PrunaAI·6 Mar

🚀 Generate a story frame by frame — then stitch it into a video. Image Next Scene Chaining: describe your story, pick shot types, and camera moves. Each frame is generated with P-Image, edited for continuity, then animated with P-Video. Full narrative videos from a single prompt. 🔗 Try the demo: dub.sh/zU0EYCw 💜 Sign up for our events: dub.sh/xYQyvyM 🎉Find all of our models: dub.sh/0TwJUoB ⭐️ Star our OSS GitHub: dub.sh/g34026M

English

0

5

23

4K

Bertrand Charpentier@Bertrand_Charp·6 Mar

According to @ArtificialAnlys, P-video is again on the efficiency/quality Pareto frontier (and also the fastest video generation model).

Artificial Analysis@ArtificialAnlys

P-Video is the fastest and cheapest video model covered by Artificial Analysis, capable of generating a 720p 5-second video in ~10 seconds! P-Video is the latest video model from @prunaAI, ranking #41 in Text to Video and #42 in Image to Video in the Artificial Analysis Video Arena, comparable to Seedance 1.0 Mini and Wan 2.2 A14B respectively. At $1.20/min for 720p and $2.40/min for 1080p, P-Video is significantly cheaper than LTX-2 Fast ($2.40/min) and MiniMax's Hailuo 2.3 ($2.80/min) while maintaining faster generation speeds. P-Video is accessible via @prunaAI's API, as well as @Replicate, @Runware, @Cloudflare, @runpod, @WiroAI, and @Qubrid_AI.

English

0

5

103

Bertrand Charpentier nag-retweet

Pruna AI@PrunaAI·5 Mar

Create an avatar talking, a social ad video, or an animated product image in seconds. Use simple Workflows with P-Video and P-Image. - Step 1: Enter a prompt - Step 2: Get/edit an image - Step 3: Generate a video in seconds with dialogue, motion, or lookbook shots. 🔗 Try the demo: dub.sh/IHLnuD0 💜 Sign up for our events: dub.sh/Ut89wKZ 🎉Find all of our models: dub.sh/Yn5VWwg ⭐️ Star our OSS GitHub: dub.sh/quN1ETR

English

2

4

21

986

Bertrand Charpentier@Bertrand_Charp·4 Mar

P-video achieves SOTA performance in terms of efficiency/quality.

Pruna AI@PrunaAI

As the cheapest and fastest video model, P-Video strongly sits on the efficiency-quality Pareto frontier The best speed-cost-to-quality trade-off among video models with public APIs. $1.20/min (Artificial Analysis) vs $4–30 for competitors. ELO 1171 (text-to-video) and 1197 (image-to-video) on arena.ai — ahead of LTX-2, Hunyuan, and in the mix with Hailuo and Seedance. Sources: @arena · @ArtificialAnlys · @replicate 🔗 Try it: dub.sh/IovIOf9 💜 Sign up for our events: dub.sh/Rh5lVZu 🎉Find all of our models: dub.sh/3YTzAMg ⭐️ Star our OSS GitHub: dub.sh/tLJc2yS

English

0

3

92

Bertrand Charpentier nag-retweet

Prodia@prodialabs·27 Şub

P-video is on Prodia! 🚀 * Use draft mode for ultra-fast video generation (5s to get 10s 720p video) * only $0.025 per 5s of video * Integrated audio * Built for real-time creative workflows * Perfect for ideation: draft → refine → publish Free gens until Monday 9am CET 🥳

English

1

5

14

1.1K

Bertrand Charpentier nag-retweet

Runware@runware·26 Şub

P-Video by @PrunaAI is now live on Runware 🔥 D0 release and free until Friday 9PM CET! this model is built for speed and cost – designed for fast iteration without breaking your workflow. so if you want to stress test it, now’s the time.

English

9

14

114

177.3K

Bertrand Charpentier@Bertrand_Charp·26 Şub

@Designarena @runwayml @Kling_ai How can we add p-video, the fastest video generation model on @Designarena ? That would be very cool :) x.com/PrunaAI/status…

Pruna AI@PrunaAI

Happy to announce P-Video, delivering the fastest and cheapest video generation on the market. • 𝗛𝗶𝗴𝗵 𝘀𝗽𝗲𝗲𝗱: 10s generation speed for 5s of 720p, 18s generation speed for 5s of 1080p video. • 𝗔𝗳𝗳𝗼𝗿𝗱𝗮𝗯𝗹𝗲: $0.02 per second of 720p video, $0.04 per second of 1080p video. • 𝗛𝗶𝗴𝗵 𝗰𝗼𝗻𝘁𝗿𝗼𝗹: A unique draft mode for video preview, taking 2.5s to preview 5s of 720p video and 4.9s to preview 5s of 1080p video. • 𝗠𝘂𝗹𝘁𝗶-𝗺𝗼𝗱𝗮𝗹: Support text, image, and audio input for up to 15s video generation for any format, with audio output support. 💨 Run it self-serve via API here: dashboard.pruna.ai/login - dashboard.pruna.ai/login -, also available on @Replicate, @Runware, @Cloudflare, @runpod, @WiroAI, @Qubrid_AI 👉 Test it in the playground: …-playground-production.up.railway.app - …-playground-production.up.railway.app - 🎡 Explore applied demos: demo.pruna.ai - demo.pruna.ai - ⭐️ Star our OSS GitHub: github.com/PrunaAI/pruna

English

1

0

4

72

Design Arena@Designarena·26 Şub

BREAKING: Grok Imagine ranks 3rd in Video Edit Arena by Design Arena with an Elo of 1245 It's in the same performance bracket as Gen-4 Aleph by @runwayml and closely behind O1 Edit by @Kling_ai This leaderboard evaluates video-to-video model performance with real user use cases Congrats to the @xai team for this achievement!

English

4

2

66

5.4K

Bertrand Charpentier nag-retweet

Pruna AI@PrunaAI·26 Şub

FREE VIDEO GENERATION, to celebrate our launch! • Until Friday 9pm CET, p-video is free for all within rate limits. • Until Monday 9pm CET, post one nice p-video creation and DM us to get 10$ in free credits on our API. Generate with P-video and share your creations!

Pruna AI@PrunaAI

Happy to announce P-Video, delivering the fastest and cheapest video generation on the market. • 𝗛𝗶𝗴𝗵 𝘀𝗽𝗲𝗲𝗱: 10s generation speed for 5s of 720p, 18s generation speed for 5s of 1080p video. • 𝗔𝗳𝗳𝗼𝗿𝗱𝗮𝗯𝗹𝗲: $0.02 per second of 720p video, $0.04 per second of 1080p video. • 𝗛𝗶𝗴𝗵 𝗰𝗼𝗻𝘁𝗿𝗼𝗹: A unique draft mode for video preview, taking 2.5s to preview 5s of 720p video and 4.9s to preview 5s of 1080p video. • 𝗠𝘂𝗹𝘁𝗶-𝗺𝗼𝗱𝗮𝗹: Support text, image, and audio input for up to 15s video generation for any format, with audio output support. 💨 Run it self-serve via API here: dashboard.pruna.ai/login - dashboard.pruna.ai/login -, also available on @Replicate, @Runware, @Cloudflare, @runpod, @WiroAI, @Qubrid_AI 👉 Test it in the playground: …-playground-production.up.railway.app - …-playground-production.up.railway.app - 🎡 Explore applied demos: demo.pruna.ai - demo.pruna.ai - ⭐️ Star our OSS GitHub: github.com/PrunaAI/pruna

English

1

5

23

1.5K

Bertrand Charpentier nag-retweet

Arena.ai@arena·26 Şub

P-Video enters the Video Arena in top 26 🇪🇺 @PrunaAI is the only EU-based foundational lab on Video Arena. A milestone in a field dominated by US and Chinese labs. This is their fastest model with pricing at $0.04/second for 1080p. Highlights: - tied for #22 in Text-to-Video, score 1178 on par with Hailuo 2.0 and Kandinsky 5.0 Pro - top 26 for Image-to-Video, score 1199 on par with Hailuo 2.0 Fast A notable debut in a fast-growing field of 35 video models in Arena. Congrats to the @PrunaAI team! 👏

Pruna AI@PrunaAI

Happy to announce P-Video, delivering the fastest and cheapest video generation on the market. • 𝗛𝗶𝗴𝗵 𝘀𝗽𝗲𝗲𝗱: 10s generation speed for 5s of 720p, 18s generation speed for 5s of 1080p video. • 𝗔𝗳𝗳𝗼𝗿𝗱𝗮𝗯𝗹𝗲: $0.02 per second of 720p video, $0.04 per second of 1080p video. • 𝗛𝗶𝗴𝗵 𝗰𝗼𝗻𝘁𝗿𝗼𝗹: A unique draft mode for video preview, taking 2.5s to preview 5s of 720p video and 4.9s to preview 5s of 1080p video. • 𝗠𝘂𝗹𝘁𝗶-𝗺𝗼𝗱𝗮𝗹: Support text, image, and audio input for up to 15s video generation for any format, with audio output support. 💨 Run it self-serve via API here: dashboard.pruna.ai/login - dashboard.pruna.ai/login -, also available on @Replicate, @Runware, @Cloudflare, @runpod, @WiroAI, @Qubrid_AI 👉 Test it in the playground: …-playground-production.up.railway.app - …-playground-production.up.railway.app - 🎡 Explore applied demos: demo.pruna.ai - demo.pruna.ai - ⭐️ Star our OSS GitHub: github.com/PrunaAI/pruna

English

5

8

79

23K

Bertrand Charpentier@Bertrand_Charp·26 Şub

The fastest video generation model is now live! You can generate videos in seconds now :) - Available on our API, @replicate , @runware, @Cloudflare, @runpod, @WiroAI, @Qubrid_AI - Evaluated on @ArtificialAnlys and @arena

Pruna AI@PrunaAI

Happy to announce P-Video, delivering the fastest and cheapest video generation on the market. • 𝗛𝗶𝗴𝗵 𝘀𝗽𝗲𝗲𝗱: 10s generation speed for 5s of 720p, 18s generation speed for 5s of 1080p video. • 𝗔𝗳𝗳𝗼𝗿𝗱𝗮𝗯𝗹𝗲: $0.02 per second of 720p video, $0.04 per second of 1080p video. • 𝗛𝗶𝗴𝗵 𝗰𝗼𝗻𝘁𝗿𝗼𝗹: A unique draft mode for video preview, taking 2.5s to preview 5s of 720p video and 4.9s to preview 5s of 1080p video. • 𝗠𝘂𝗹𝘁𝗶-𝗺𝗼𝗱𝗮𝗹: Support text, image, and audio input for up to 15s video generation for any format, with audio output support. 💨 Run it self-serve via API here: dashboard.pruna.ai/login - dashboard.pruna.ai/login -, also available on @Replicate, @Runware, @Cloudflare, @runpod, @WiroAI, @Qubrid_AI 👉 Test it in the playground: …-playground-production.up.railway.app - …-playground-production.up.railway.app - 🎡 Explore applied demos: demo.pruna.ai - demo.pruna.ai - ⭐️ Star our OSS GitHub: github.com/PrunaAI/pruna

English

4

2

20

563

Bertrand Charpentier nag-retweet

Pruna AI@PrunaAI·25 Şub

🎓 Last week, we were happy to welcome @Chenfeng_X to our webinar. He introduced us to streaming systems and explained how we can unlock real-time diffusion by reorganizing implementation patterns to achieve significant inference speedups. • How stream-optimized diffusion pipelines can jump from “barely interactive” to genuinely real-time. • Why some common parallelism approaches don’t scale linearly—and how GPU pipeline orchestration can get you gains. • Video generation can be brutally memory-hungry, making cache efficiency a first-class problem. If you’re building with diffusion and want 𝘳𝘦𝘢𝘭 𝘴𝘱𝘦𝘦𝘥, don’t miss the recording. Watch it here 👉 youtu.be/icJXGF3kxto And if you joined live—what part of the stack is 𝘺𝘰𝘶𝘳 biggest bottleneck right now?

YouTube

English

0

2

4

650

Bertrand Charpentier

Tuklasin