Benjamin Aubin @benjaminaubin.bsky.social · 13/05/2025Thrilled to finally release the training code and checkpoints (with non-commercial license) of our Latent Bridge Matching work ! 000
Reposted by Benjamin AubinClément Chadebec @clementchadebec.bsky.social · 13/05/2025📢 Latent Bridge Matching update! 📢 New Jasper Research release 🚀 - 3 LBM models on @hf.co (relighting, depth, normals) - LBM training code Also see our @gradio-hf.bsky.social space for object relighting! 🤗 huggingface.co/jasperai/LBM... 💻 github.com/gojasper/LBM 📗 arxiv.org/abs/2503.07535 263
Reposted by Benjamin AubinClément Chadebec @clementchadebec.bsky.social · 13/03/2025Excited to share our new research at Jasper Research! 🚀 LBM: Latent Bridge Matching for Fast Image-to-Image Translation Try out our @hf.co space for object relighting! 🤗 @gradio-hf.bsky.social demo: huggingface.co/spaces/jaspe... 👉 Paper: arxiv.org/abs/2503.07535 💻 Repo: github.com/gojasper/LBM 2207
Reposted by Benjamin Aubinonurxtasar.bsky.social @onurxtasar.bsky.social · 17/12/2024Jasper research is releasing their latest research. Our 1-step diffusion model can create realistic shadows for object images in under a second, while giving you control over shadow direction, softness, intensity 👇 @clementchadebec.bsky.social, @benjaminaubin.bsky.social, @damien-henry.bsky.social 284
Benjamin Aubin @benjaminaubin.bsky.social · 17/12/2024Very excited to share our latest work on Controllable Shadows 🔦 👉🏼 gojasper.github.io/controllable...lnkd.inLinkedInThis link will take you to a page that’s not on LinkedIn 030
Benjamin Aubin @benjaminaubin.bsky.social · 12/12/2024Congrats @clementchadebec.bsky.social, @onurxtasar.bsky.social, @damien-henry.bsky.social and the whole Jasper & Clipdrop research team 🎉 030
Reposted by Benjamin AubinClément Chadebec @clementchadebec.bsky.social · 12/12/2024🎉 Very happy to share that Jasper Research's very first research paper, Flash Diffusion just got accepted to AAAI 2025. This paper introduces a novel and flexible distillation method designed to speed up image generation with diffusion models. 👉 Paper: arxiv.org/abs/2406.02347 283