
Eyal π
@_Shaamallow
Followers
147
Following
9K
Media
18
Statuses
281
Research Intern at @IAatMeta, ex @Polytechnique, @Clipdropapp by @heyjasperai
Online
Joined December 2015
π Excited to launch Texture Diffusion, an open-source Blender add-on that brings the power of diffusion models to texture generation! π¨. β¨ Features:.π― Inpainting for precise texture edits.π Support for LoRAs & IP-Adapters.π€ Seamless integration into Blenderβs workflow
4
27
155
RT @3blue1brown: New video on the details of diffusion models: Produced by @welchlabs, this is the first in a smalβ¦.
0
402
0
RT @ni_jovanovic: There's a lot of work now on LLM watermarking. But can we extend this to transformers trained for autoregressive image geβ¦.
0
54
0
RT @BaldassarreFe: DINOv2 meets text at #CVPR 2025! Why choose between high-quality DINO features and CLIP-style vision-language alignment?β¦.
0
103
0
RT @CChadebec: Excited to share our new research at @heyjasperai !π. LBM: Latent Bridge Matching for Fast Image-to-Image Translation. Try oβ¦.
0
53
0
RT @onurxtasar: We (@heyjasperai / @clipdropapp research team) are excited to announce the release of our latest research project on fast aβ¦.
0
39
0
RT @CChadebec: πΒ Very happy to share that @heyjasperai's very first research paper, Flash Diffusion just got accepted to #AAAI. This paperβ¦.
0
7
0
RT @BlenderStudio_: The Blender Studio team is proud to release Project Gold, a technical showcase focused on stylized rendering, along witβ¦.
0
298
0
RT @windblowngame: Prepare yourselves Leapers. The storm has arrived. πͺοΈ . Windblown is OUT NOW in Steam Early Access!. π«1-3 player onlβ¦.
0
210
0
I want to thank the amazing team at @clipdropapp by @heyjasper for this great internship. Looking forward to being working with the team in the future. π.
1
0
5
We also worked on a variation of the popular InstantStyle method by adding a noisy DDIM inversion. You can check our @gradio demo with the link below:
1
2
9
Our team at Jasper Research @heyjasperai has just released Style-Rank π¨, a fair and unified benchmark of open-source training-free styling methods. Our evaluation is performed on our Style-Rank evaluation set, compiled from multiple styling papers and provided on @huggingface.
3
11
32