🔥🔥 Today we, @clipdropapp are launching our 💡image relighting #AI application 💡. The app allows you to apply professional lights to your portrait images 📸 in real time ⚡. Try it now! it is free 🙂. #photography #MachineLearning

RT @heyjasperai: We’re thrilled to announce that the Jasper Research team’s latest paper on Latent Bridge Matching (LBM) was accepted to th….

RT @heyjasperai: Proud to share the latest breakthrough from Jasper Research: Latent Bridge Matching (LBM) just got a major update!. Our te….

RT @CChadebec: 📢 Latent Bridge Matching update! 📢. New @heyjasperai release 🚀. - 3 LBM models on @huggingface (relighting, depth, normals)….

RT @heyjasperai: New research drop! Our team at Jasper is redefining image-to-image translation with LBM: Latent Bridge Matching—a scalable….

Thrilled to share our new research on image-to-image translation, demonstrating strong performance across tasks like object relighting, shadow prediction, object removal, and depth and surface normal estimation. Check out our research paper, project page, demo, and Github repo👇.

RT @heyjasperai: We had an incredible time last Saturday at the prestigious International @RealAAAI Conference in Philadelphia! Jasper’s re….

Our blog post introducing our new research on controllable shadow generation using single-step diffusion models trained on fully synthetic data👇.

In the absence of a public benchmark on the topic of controllable shadow generation, we created a synthetic test set with three distinct tracks: horizontal direction control, vertical direction control, and softness control. The test set is publicly available on @huggingface 🤗.

During the training stage of the diffusion model, we incorporated polar and azimuthal angles along with the light size parameter into the denoiser using vector conditioning. This conditioning mechanism allows precise control over the shadow direction and softness. By training the

To position the 3D model, camera, and area light, we utilized the spherical coordinate system, as illustrated in the figure below. Theta and phi denote the polar and azimuthal angles, respectively. The variable "s" defines the size of the area light, determining the softness of

The biggest challenge was to create a training set for this task. We collected a diverse set of 3D models and leveraged @Blender to generate a large dataset tailored specifically to this task. For every 3D model, we generated an object image, an object mask, and a shadow map

We (@heyjasperai / @clipdropapp research team) are excited to announce the release of our latest research project on fast and controllable shadow generation. Our 1-step diffusion model can create realistic shadows for object images in under a second ⚡️, while giving you precise

RT @heyjasperai: Proud moment for Jasper Research: “Flash Diffusion,” our paper on a new method designed to enhance the efficiency and spee….

RT @CChadebec: 🎉 Very happy to share that @heyjasperai's very first research paper, Flash Diffusion just got accepted to #AAAI. This paper….

RT @_Shaamallow: 🚀 Excited to launch Texture Diffusion, an open-source Blender add-on that brings the power of diffusion models to texture….

RT @_Shaamallow: Our team at Jasper Research @heyjasperai has just released Style-Rank 🎨, a fair and unified benchmark of open-source train….

RT @CChadebec: New @heyjasperai research release 🚀. Upscaler, depth and normal maps ControlNets for FLUX.1-dev by @bfl_ml . @huggingface Mo….

RT @_Shaamallow: FlashSDXL is compatible with existing LoRA without any additional training !.New @Gradio Space on @huggingface🤗based on @m….

RT @CChadebec: Flash #SD3 is out!. Today, we release a 90M LoRA of #SD3 able to generate in just 4 steps. Model was trained for ~50h on 2 H….

RT @Gradio: ⚡𝐅𝐥𝐚𝐬𝐡 𝐃𝐢𝐟𝐟𝐮𝐬𝐢𝐨𝐧, a diffusion distillation method. ⚗️ A 66.5M LoRA model, which is a distilled version of the famous Pixart-α m….