🔥Telegram İfşa

Super excited to share what we've been working on at Pika! 🚀🚀🚀

TL;DR - we improve text-to-image output quality by tuning an LLM to predict ComfyUI workflows tailored to each generation prompt Project page: comfygen-paper.github.io Paper: arxiv.org/abs/2410.01731 [1\4]

[NEW Preprint] 🔔🔔 CLoSD embeds real-time Motion Diffusion into a multi-task RL agent. Performing a task is as easy as describing it with a text prompt! Want to move to the next task? Just change the prompt on the fly😁 [1/4]🧵 guytevet.github.io/CLoSD-page/

Ever wondered how a SINGLE token represents all subject regions in personalization? Many methods use this token in cross-attention, meaning all semantic parts share the same single attention value. We present Nested Attention, a mechanism that generates localized attention values

[1/5] Rethinking SVGs, the implicit way — meet NeuralSVG! 🎨✨ An implicit neural representation for generating layered SVGs from text prompts. 💧 Powered by SDS and nested-dropout for ordered shapes 🖌️ Enables inference-time editing like color palette & aspect ratio Read more on

What if you could compose videos— merging multiple clips, even capturing complex athletic moves where video models struggle - all while preserving motion and context? And yes, you can still edit them with text after! Stay tuned for more results. #AI #VideoGeneration #SnapResearch

🚀 Meet DiP: our newest text-to-motion diffusion model! ✨ Ultra-fast generation ♾️ Creates endless, dynamic motions 🔄 Seamlessly switch prompts on the fly Best of all, it's now available in the MDM codebase: github.com/GuyTevet/motio… [1/3]

Excited to introduce our new work: ImageRAG 🖼️✨ rotem-shalev.github.io/ImageRAG We enhance off-the-shelf generative models with Retrieval-Augmented Generation (RAG) for unknown concept generation, using a VLM-based approach that’s easy to integrate with new & existing models! [1/3]

🚀 New preprint! 🚀 Check out AnyTop 🤩 ✅ A diffusion model that generates motion for arbitrary skeletons 🦴 ✅ Using only a skeletal structure as input ✅ Learns semantic correspondences across diverse skeletons 🦅🐒🪲 🔗 Arxiv: arxiv.org/abs/2502.17327

“Tight Inversion” uses an IP-Adapter during DDIM inversion to preserve the original image better when editing. arxiv.org/abs/2502.20376

Vectorization into a neat SVG!🎨✨ Instead of generating a messy SVG (left), we produce a structured, compact representation (right) - enhancing usability for editing and modification. Accepted to #CVPR2025 !

Ever stared at a set of shapes and thought: 'These could be something… but what?' Designed for visual ideation, PiT takes a set of concepts and interprets them as parts within a target domain, assembling them together while also sampling missing parts. eladrich.github.io/PiT/

🔔just landed: IP Composer🎨 semantically mix & match visual concepts from images ❌ text prompts can't always capture visual nuances ❌ visual input based methods often need training / don't allow fine grained control over *which* concepts to extract from our input images So👇

Excited to share that "TokenVerse: Versatile Multi-concept Personalization in Token Modulation Space" got accepted to SIGGRAPH 2025! It tackles disentangling complex visual concepts from as little as a single image and re-composing concepts across multiple images into a coherent

🔔Excited to announce that #AnyTop has been accepted to #SIGGRAPH2025!🥳 ✅ A diffusion model that generates motion for arbitrary skeletons ✅ Using only a skeletal structure as input ✅ Learns semantic correspondences across diverse skeletons 🌐 Project: anytop2025.github.io/Anytop-page

Excited to share that "IP-Composer: Semantic Composition of Visual Concepts" got accepted to #SIGGRAPH2025!🥳 We show how to combine visual concepts from multiple input images by projecting them into CLIP subspaces - no training, just neat embedding math✨ Really enjoyed working