Thanks AK for sharing our work. Editing with pre-trained text-to-audio models is as simple as ever. No need for test-time optimization. With Hila Manor we explore zero-shot methods for both text-based editing and unsupervised modifications. hilamanor.github.io/AudioEditing/

Must diffusion models use a denoising objective? Check out our Classification Diffusion Models, which are based on classification rather than denoising. shaharyadin.github.io/CDM/

Edit-friendly DDPM inversion has been accepted for cvpr_2024 🎉 Code: github.com/inbarhub/DDPM_… Project page: inbarhub.github.io/DDPM_inversion/ Check out our space (thanks Linoy Tsaban🎗️) to edit your own images: huggingface.co/spaces/linoyts… W/ the amazing Tomer Michaeli Vova Kulikov

Our (Tomer Michaeli) Text-Based Audio Editing method now has an interactive space🤗 🎶Try it out on your own audio🎶: huggingface.co/spaces/hilaman… Paper: arxiv.org/abs/2402.10009 Project page: hilamanor.github.io/AudioEditing/

Everything THREE! Claude and Stable Diffusion! Plus: Music Editing w/ Zeta (ft Hila Manor), and a look at Relighting in Skyglass from Beeble LINK: youtu.be/mw0-AiJbQiY

Excited to share that our (Tomer Michaeli) paper, "On the Posterior Distribution in Denoising: Application to Uncertainty Quantification", was accepted to #ICLR2024! I'm going to be at ICLR 2026 all week, come to my poster on May 8th (session 3, #218)! hilamanor.github.io/GaussianDenois…

Excited to be in Vienna presenting our paper "From Posterior Sampling to Meaningful Diversity in Image Restoration" at #ICLR2024! (poster #77 at session 1) Grateful to my amazing co-authors Hila Manor Yuval Bahat Tomer Michaeli project page: noa-cohen.github.io/MeaningfulDive…

Accepted to #ICML2024! 🥳 🎬Slicedit: Zero-Shot Video Editing With Text-to-Image Diffusion Models Using Spatio-Temporal Slices🎬 ICML Conference Website: matankleiner.github.io/slicedit/ Paper: arxiv.org/abs/2405.12211 W/ the amazing Nathaniel Cohen Vova Kulikov matan kleiner Tomer Michaeli

How many input-output pairs from a trained model are required for stealing it? It turns out that for many image-restoration and image-to-image translation models, the answer is - ONLY ONE! Check out our paper (w/ Nurit Spingarn): arxiv.org/abs/2406.00828

#cvpr2024 Want to see me as wonder woman, Vova Kulikov as superman, and Tomer Michaeli as ironman? DDPM inversion poster, tomorrow, Thursday 10:30 am, poster no 275!

Posterior sampling for solving inverse problems? No thanks😉 Check out our new photo-realistic image restoration algorithm: Posterior-Mean Rectified Flow (PMRF). It (provably) outperforms posterior sampling. Project page: pmrf-ml.github.io (w/Tomer Michaeli)

FlowEdit allows editing real images with pre-trained text-to-image flow models. It is: - Optimization free - Model agnostic - Doesn't rely on inversion! Inbar Huberman-Spiegelglas, Vova Kulikov, matan kleiner

Excited to present DDCM📖 with Guy Ohayon, Tomer Michaeli & M. Elad🎉 DDCM is a new generative approach that achieves SotA compression and is extendable to compressed conditional synthesis, all just w/ pre-trained diffusion models. Webpage &🤗Demo: ddcm-2025.github.io

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

Thrilled to share that our paper TokenVerse received a Best Paper Award at #SIGGRAPH2025! 🎉

Hila Manor and I will present our work tomorrow at ICML Conference, 4:30PM😊 Stop by our poster to learn more about compressed image generation using diffusion models!

📷  FlowEdit has been accepted to #ICCV2025 Edit real images with text-to-image flow models! Check out: code github.com/fallenshock/Fl… webpage matankleiner.github.io/flowedit/ space to edit your images - huggingface.co/spaces/fallens… great ComfyUI plugins (logtd) matankleiner.github.io/flowedit/#comfy

🎉 Excited to share that FlowEdit paper got accepted as an ORAL presentation at #ICCV2025! 🎉 See you in Honolulu! 🌺 Thanks to the amazing team Vova Kulikov, matan kleiner, Tomer Michaeli