iiinova — where your digital self keeps evolving

Pruna AI @prunaai.bsky.social · 03/07/2026

Same models, same garments, consistent try-ons but the dedicated model is much faster and a lot cheaper. Fit up to 11 garments onto a person's photo — flat-lay, product shots, worn photos, or multi-garment references. Try it yourself: pruna-playground-production-861e.up.railway.app/p-image-try-on

000

Pruna AI @prunaai.bsky.social · 02/07/2026

How does Pruna OSS orchestrate model optimization under the hood? Our latest community blog, contributed by Parag Ekbote (thank you for the amazing blog!), explores how Pruna optimizes models by tracing the smash function and DAG execution. Read it in the Pruna blog: www.pruna.ai/blog/how-pru...

pruna.ai

How Pruna Optimizes Models: Tracing the Smash Function and DAG Execution - Pruna AI

Faster, cheaper, smaller, greener AI Models with outstanding quality

110

Pruna AI @prunaai.bsky.social · 22/06/2026

Smash your model to make it faster, smaller, cheaper, and greener following just 5 steps: 1. load a pretrained model 2. define optimizations with a SmashConfig 3. apply optimizations with smash 4. evaluate the optimized model with the EvaluationAgent 5. run inference with the optimized model

100

Pruna AI @prunaai.bsky.social · 16/06/2026

Contributing to Pruna is now easier! Whether you’re an OSS expert or contributing for the first time, we’ve improved our contribution guide to make the process clearer. Here’s how to get started 👇

100

Pruna AI @prunaai.bsky.social · 09/06/2026

Pruna OSS Community Spotlight: KVPress by kschwethelm KVPress makes 20 KV cache compression strategies available for causal language models. KVPress compresses the key-value cache during the pre-fill phase, reducing memory usage for long-context inference.

110

Pruna AI @prunaai.bsky.social · 05/06/2026

💜 Simply make AI models faster, cheaper, smaller, greener! The toolkit is designed with simplicity in mind - requiring just a few lines of code to optimize your models. It supports various model types, including LLMs, Diffusion, and more! ⭐️ Give us a star: github.com/PrunaAI/pruna

100

Pruna AI @prunaai.bsky.social · 04/06/2026

Have you tried our playground yet? It offers easy onboarding for using any of our models and showcases some cool example generations! Check it out here: pruna-playground-production-861e.up.railway.app

pruna-playground-production-861e.up.railway.app

Pruna AI Playground

Test and validate our performand, fast and cheap Performance models for AI content generation.

100

Pruna AI @prunaai.bsky.social · 04/06/2026

P-Video-Replace is now the fastest model for top-quality character replacement in existing video. - $0.03/s at 720p and $0.06/s at 1080p - 3.58 s generation time per second of output video Try it in the playground: p-video-playground-production.up.railway.app/p-video-repl...

000

Pruna AI @prunaai.bsky.social · 03/06/2026

Hell Yeah! Runware just published a practical guide for P-Video-Animate and wanted to share it with you! - $0.03/s at 720p and $0.06/s at 1080p - ~5s generation time per second of output video Their guide covers the image/video pairing, prompt steering, and more! runware.ai/docs/models/...

runware.ai

Animating images with a source video — P-Video-Animate API

How to use P-Video-Animate to animate a reference image with the motion, timing, and camera movement from a source video. Covers the pairing rule, optional prompt steering, and four concrete patterns.

100

Pruna AI @prunaai.bsky.social · 02/06/2026

Cheap and Fast AI Animation of Motion For Still Images | Scenario x P-Video-Animate See how Scenario's used our P-Video-Animate model for a cool launch video and use it yourself. Fast, high-quality generation, and light on credits. Try the model: www.scenario.com/models/p-vid...

100

Pruna AI @prunaai.bsky.social · 29/05/2026

Transfer Motion, Acting and Camera Movement with AI Editing | Wavespeed 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: wavespeed.ai/models?keywo... Check out all our model: www.pruna.ai/all-models

000

Pruna AI @prunaai.bsky.social · 27/05/2026

Pruna OSS Community Spotlight: Token Merging by rensortino Token Merging is now available for vision transformer models.

100

Pruna AI @prunaai.bsky.social · 25/05/2026

How can we make systems more sustainable in the era of AI? This is one of the questions that has been driving us at Pruna.

100

Pruna AI @prunaai.bsky.social · 04/05/2026

P-Video-Avatar is the fastest and most cost-effective avatar video model available, and launching end-to-end generation workflows has never been easier! Learn more about the model: www.pruna.ai/p-video-avatar Check out the skill: skills.sh/infsh-skills...

skills.sh

p-video-avatar by infsh-skills/skills

Install the p-video-avatar skill for your AI agent. Published by infsh-skills/skills.

000

Pruna AI @prunaai.bsky.social · 04/05/2026

🚀 Pruna 0.3.3 is out! Here are a few highlights: - New benchmarking and evaluation tools. - Algorithm and compatibility upgrades. - Support for Python 3.13. - A wide range of bug fixes and reliability improvements. Thank you all for your contribution! 👉 Read the notes: github.com/PrunaAI/prun...

github.com

GitHub - PrunaAI/pruna: Pruna is a model optimization framework built for developers, enabling you to deliver faster, more efficient models with minimal overhead.

Pruna is a model optimization framework built for developers, enabling you to deliver faster, more efficient models with minimal overhead. - PrunaAI/pruna

100

Pruna AI @prunaai.bsky.social · 30/04/2026

P-Video-Avatar is now the fastest model for top-quality avatar generation. - It costs 0.025$ per second of video, and takes 1.83s generation time per second of video. - It offers high control, audio support in 20+ languages, and long-form video. 📚 API & quickstart: www.pruna.ai/p-video-avatar

000

Pruna AI @prunaai.bsky.social · 29/04/2026

Learn how to make the latest image generation models smaller and faster without sacrificing quality. In this tutorial, we smashed FLUX.2 Klein 4B, one of the latest open-source models, and used FORA, TorchAO, and torch.compile to achieve a 2–3× speedup.

100

Pruna AI @prunaai.bsky.social · 27/04/2026

Introducing the Pruna Build Program 🚀 Most AI teams hit the same wall: they build a great product, but inference costs make scaling hard. This is for teams building something real and thinking about cost, speed, and efficiency. Start with $300 in free credits and unlock more as usage grows.

100

Pruna AI @prunaai.bsky.social · 24/04/2026

First Prune is almost over 🔥 This is our last call for anyone who wants to contribute to Pruna OSS. Join before April 30: pick an open issue, ask to be assigned, and submit your PR. 👉 Search for your issue: github.com/PrunaAI/prun... 👉 Read more about Pruna OSS: www.pruna.ai/blog/first-p...

000

Pruna AI @prunaai.bsky.social · 20/04/2026

We launched two speedy diffusion language model endpoints. llada2.1-mini hits ~1000+ TPS; llada2.1-flash reaches ~800+ TPS for fast, high-volume language tasks. See them on Replicate: replicate.com/prunaai/llad... ⭐️ Star our OSS: github.com/PrunaAI/pruna

replicate.com

prunaai/llada2.1-mini – Replicate

The fastest diffusion language model with up to ~1000+ tps

000

Pruna AI @prunaai.bsky.social · 17/04/2026

Loved the energy at our AI Efficiency Meetup in Munich last Wednesday! Special thanks to our speakers, Hamza Tahir and Begüm Cig, for their time, insights, and great discussions. And of course, thanks to everyone who came by, asked thoughtful questions, and made the event so enjoyable.

000

Pruna AI @prunaai.bsky.social · 16/04/2026

We just launched two new models on Replicate! • ERNIE-Image → higher quality (~33s) • ERNIE-Image-Turbo → faster iteration (~6s) No prompt engineering required — our built-in prompt enhancer handles it. Try them: replicate.com/prunaai/erni... replicate.com/prunaai/erni...

replicate.com

prunaai/ernie-image – Replicate

ERNIE-Image is an open text-to-image generation model developed by the ERNIE-Image team at Baidu

000

Pruna AI @prunaai.bsky.social · 15/04/2026

Pruna welcomes Adrien Fradin as ML Research intern. He’s finishing his Master at MVA after Applied Math at École polytechnique. Excited to have his expertise on board. 📚 API & quickstart: docs.api.pruna.ai/guides/quick...

000

Pruna AI @prunaai.bsky.social · 15/04/2026

First Prune is halfway 🚀 with something special: - A recap blog post about our OSS journey: how we started, what we’ve built, and what’s next. - And a surprise: now each merged PR earns 60 credits. 👉 Read the blog: www.pruna.ai/blog/first-p... 👉 Search for your issue: github.com/PrunaAI/prun...

000

Pruna AI @prunaai.bsky.social · 14/04/2026

Join us in Munich tomorrow, April 15, for our AI efficiency meetup! We’ll hear from: Hamza Tahir from ZenML Begüm Cig from Pruna AI 👉 Learn more and sign up: buff.ly/LLLWHDL

000

Pruna AI @prunaai.bsky.social · 14/04/2026

Pruna AI’s optimized fast endpoints for GPT-OSS-20B and 120B are now available. Faster model responses at replicate.com/prunaai/gpt-... and replicate.com/prunaai/gpt-.... Give them a try! ⭐️ Star our OSS: github.com/PrunaAI/pruna

replicate.com

prunaai/gpt-oss-20b-fast – Replicate

Advanced 20B open-weight reasoning models to customize for any use case and run anywhere.

000

Pruna AI @prunaai.bsky.social · 13/04/2026

Qwen-3.5-35B-A3B-Fast performance up with MoE kernel tuning—throughput doubled and TTFT reduced by 30% compared to competitors. Ready for high-load AI serving! Details at replicate.com/prunaai/qwen...

replicate.com

000

Pruna AI @prunaai.bsky.social · 10/04/2026

Mehdi Si-mohammed from ENS Paris-Saclay joins Pruna as an ML Research intern. His expertise in HPC and applied math strengthens our AI research efforts. Welcome aboard, Mehdi! 📚 API & quickstart: docs.api.pruna.ai/guides/quick...

000

Pruna AI @prunaai.bsky.social · 09/04/2026

First Prune is in progress 🌱 If you want to join, there’s still time! Each merged PR in April earns 30 Pruna API credits. Don't hesitate to contact us if you have questions— we’ll be here to help. 👉 Explore the open issues here: buff.ly/qVPCFdb ⭐️ Star our OSS: github.com/PrunaAI/pruna

000

Pruna AI @prunaai.bsky.social · 09/04/2026

Models are getting fast. We make them faster. 🚀 We just deployed optimized inference for Google's Gemma 4 26B on @replicate.com, and we've managed to squeeze performance a lot against other deployments: ⚡ +20% throughput ⏱️ -50% time to first token 👉 Try it yourself: replicate.com/prunaai/gemm...

replicate.com

prunaai/gemma-4-26b-a4b-fast – Replicate

This is a version of the MoE Gemma 4 26B optimised by Pruna AI.

000

Pruna AI @prunaai.bsky.social · 08/04/2026

P-Image-Upscale runs in less than 1 second for $0.005 up to 8 MP with creative and detail options! Get more info at: pruna.ai/p-image-upsc... Sign up for the Pruna API: dashboard.pruna.ai Try it on Replicate: replicate.com/deployments/... Try it on Runware: runware.ai/docs/models/...

010

Pruna AI @prunaai.bsky.social · 07/04/2026

Join us in Munich on April 15 for our AI efficiency meetup! We’ll hear from: Flavius Burca from Surogate Hamza Tahir from ZenML Begüm Cig from Pruna AI 👉 Learn more and sign up: buff.ly/LLLWHDL

000

Pruna AI @prunaai.bsky.social · 07/04/2026

A call for frugal AI enthusiasts and PyTorch conference attendees: CodeCarbon, Pruna & Ecologits are hosting an event after the PyTorch conference ends on April 8th! Sign up here: luma.com/vr2ahb8c

luma.com

CodeCarbon x Pruna x Ecologits Frugal AI party · Luma

A call for frugal AI enthusiasts, and PyTorch conference attendees : CodeCarbon, Pruna & Ecologits are hosting an event after the PyTorch conference ends,…

100

Pruna AI @prunaai.bsky.social · 03/04/2026

Want to join First Prune? 🎂 Pick an open issue, submit your PR, and mark it ready for review by April 30. Each merged PR earns 30 credits redeemable on the Pruna Inference API. Check them here: github.com/PrunaAI/prun...

000

Pruna AI @prunaai.bsky.social · 01/04/2026

Ready to make AI more efficient? Our AI Efficiency Courses cover LLM architectures, compression, quantization, and finetuning with hands-on exercises. Perfect for anyone ready to optimize AI beyond just size. Start learning here: github.com/PrunaAI/ai-e...

github.com

GitHub - PrunaAI/ai-efficiency-courses: Courses on building, compressing, evaluating, and deploying efficient AI models.

Courses on building, compressing, evaluating, and deploying efficient AI models. - PrunaAI/ai-efficiency-courses

000

Pruna AI @prunaai.bsky.social · 31/03/2026

Pruna’s 1-year anniversary calls for the First Prune initiative! 🎉 Contribute by April 30 to earn Pruna Inference API credits . Find out more, check open issues, and get started: github.com/PrunaAI/pruna

000

Pruna AI @prunaai.bsky.social · 27/03/2026

Join the Resilient AI Challenge! Create energy-efficient compressed AI models for audio, image, or text tasks. Help make AI smarter, accessible, and sustainable for all. Register today and lead AI innovation! Register here: www.sustainableaicoalition.org/resilient-ai...

sustainableaicoalition.org

Resilient AI Challenge - Coalition for Sustainable AI

The rapid development of artificial intelligence represents a major transformation, affecting economies, public services, and everyday life. Yet AI’s

000

Pruna AI @prunaai.bsky.social · 26/03/2026

🎬🔚 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 easily. Sign up for our API: dashboard.pruna.ai/login Try our endpoint guides: docs.pruna.ai/en/stable/do... Star our OSS: github.com/PrunaAI/pruna

000

Pruna AI @prunaai.bsky.social · 25/03/2026

⚡️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/do... Star our OSS: github.com/PrunaAI/pruna

000

Pruna AI @prunaai.bsky.social · 23/03/2026

A call for frugal AI enthusiasts and PyTorch conference attendees: CodeCarbon, Pruna & Ecologits are hosting an event after the PyTorch conference ends on April 8th! Sign up here: luma.com/vr2ahb8c

luma.com

CodeCarbon x Pruna x Ecologits Frugal AI party · Luma

A call for frugal AI enthusiasts, and PyTorch conference attendees : CodeCarbon, Pruna & Ecologits are hosting an event after the PyTorch conference ends,…

100

Pruna AI @prunaai.bsky.social · 04/03/2025

🚀 𝟭𝟬,𝟬𝟬𝟬 𝗠𝗼𝗱𝗲𝗹𝘀 𝗦𝗺𝗮𝘀𝗵𝗲𝗱 𝗼𝗻 @hf.co 🤗 (+2,500 in just the last two months 📈 all of you are keeping us busy!) To celebrate, we gave our HF space a little makeover… and snuck in an Easter Egg 🥚 👀 Think you can find it? Drop a comment if you do!

012

Pruna AI @prunaai.bsky.social · 25/02/2025

We've been optimizing Machine Learning models on @replicate.com and seeing consistent 2-5x speedups while reducing costs, without changing how the model behaves. - Our step-by-step guide: www.pruna.ai/blog/guide-r... - Public demo space to try it out: replicate.com/prunaai

000

Pruna AI @prunaai.bsky.social · 25/02/2025

Next Tuesday, 4th of march, office hours will be about our latest integrations: Replicate, Comfy UI and Triton. John, our CTO will be present to answer all your questions! 😍 Tuesday 4th of March, 5PM CET: discord.gg/9D8JsjRx?eve...

001

Pruna AI @prunaai.bsky.social · 12/12/2024

Big news for the AI community! Pruna AI is now free(mium)! 🎉 It takes a based model as input and returns a compressed model as output with various compression methods. You can access via: - Self-hosted w/ CLI (docs.pruna.ai/en/latest/se...) - Cloud hosted w/ AWS: aws.amazon.com/marketplace/...).

docs.pruna.ai

Installing Pruna with Pip and Conda | Pruna documentation

111