Richard Zhang
@rzhang88
Followers
8K
Following
1K
Media
83
Statuses
350
Sr Research Scientist @AdobeResearch PhD @berkeley_ai, BS/MEng @cornellece 🤖 Computer vision, deep learning, graphics
San Francisco, CA
Joined March 2010
RT @rohitgandikota: Can you ask a Diffusion Model to break down a concept? 👀. SliderSpace 🚀 reveals maps of the visual knowledge naturally….
0
62
0
RT @ShengYuWang6: I will be presenting this at #NeurIPS2024 today! Come if interested :). - Wed 11 Dec 4:30 — 7:30 pm.- East Exhibit Hall A….
0
8
0
RT @ShengYuWang6: Generative models create an image inspired by the training data. But which training data are used to synthesize an image?….
0
21
0
RT @TianweiY: Video diffusion models generate high-quality videos but are too slow for interactive applications. We @MIT_CSAIL @AdobeResea….
0
112
0
RT @nupurkmr9: Check out our #SIGGRAPHASIA2024 technical paper, CustomDiffusion360, that adds object viewpoint control during customization….
0
8
0
RT @minguk_kang: We're excited to introduce our new 1-step image generator, Diffusion2GAN at #ECCV2024, which enables ODE-preserving 1k ima….
0
49
0
I'll be speaking about Data Attribution, including our recently accepted NeurIPS 2024 paper: Work w/ @ShengYuWang6, @AaronHertzmann, @junyanz89, A. A. Efros. AI4VA workshop @eccvconf, 11:45am at Amber Room 2. See you there!
0
8
94
(4/3) Links with additional information.Webpage: Paper: Project video:
0
1
4
This is an exciting area! In fact, there was another TurboEdit paper recently, from Tel Aviv & Nvidia: 3/3.
We've released the code for our #SIGGRAPHAsia2024 TurboEdit paper, where we edit images in 3 steps using SDXL-Turbo 🚀. If you're a fan of the name, you can also check out the concurrent TurboEdit by Adobe ( or even upload your own!.
1
0
14
Long, automatically-generated text prompts offer "handles" for disentangled control. Users can either directly edit the prompt or provide an instruction, and adjust the strength of the edit. Here, we show black→white cat, straight→curly hair, old→young, and add snow. 2/
1
0
2
We introduce TurboEdit -- simple text-based image editing in 1/2 sec! We leverage few-step diffusion models, mapping real images into noise with an encoder. Please see our #ECCV2024 paper: Work w/ @zongze_wu, Nick Kolkin, Jon Brandt, @elishechtman. 1/
7
85
462
RT @YotamNitzan: LazyDiffusion is accepted to #ECCV2024! . Traditional image editing methods regenerate unchanged pixels, wasting time and….
0
41
0
Happening soon! Following talks from @junyanz89 and @SergeyTulyakov. Summit 423-425 in the GenAI Media Generation workshop:
0
1
9
I'll speak about reconnecting creators with GenAI models at these #CVPR2024 Mon workshops:.- 11:25am @ Fair, Data-Efficient & Trusted CV (Arch 303).- 2:30pm @ GenAI Media Generation (Summit 423-425). Will cover Model customization, Ablation, and Data attribution. See you there!
2
7
80
RT @MIT_CSAIL: Diffusion models generate high-quality images but require hundreds of forward passes. @MIT_CSAIL and @AdobeResearch introdu….
0
62
0