user avatar
Patrick Esser
@pess_r
Walking on the generative side of computer vision @bfl_ml . he/him
Heidelberg
github.com/pesser/
Joined September 2016
344
Following
5,502
Followers
Posts
  • Pinned
    user avatar
    Patrick Esser
    @pess_r
    Aug 11, 2022
    #stablediffusion text-to-image checkpoints are now available for research purposes upon request at github.com/CompVis/stable… Working on a more permissive release & inpainting checkpoints. Soon™ coming to @runwayml for text-to-video-editing
    00:00
  • user avatar
    Patrick Esser
    @pess_r
    Oct 18, 2022
    The model behind Erase & Replace is now available at github.com/runwayml/stabl… @runwayml jointly with @robrombach
    00:00
  • user avatar
    Patrick Esser
    @pess_r
    Jan 18, 2021
    Watching transformers do their thing in 3D github.com/CompVis/taming…
    00:00
  • user avatar
    Patrick Esser
    @pess_r
    Jan 4, 2021
    Pre-tamed transformers now at github.com/CompVis/taming… Just added a Colab demo to start sampling right away: colab.research.google.com/github/CompVis…
    00:00
  • user avatar
    Patrick Esser
    @pess_r
    Jun 23, 2022
    We present Latent Diffusion Models in tomorrow's Image & Video Synthesis and Generation session @CVPR in Hall B1 (Thur. 08:30-10:18). Join us for a chat at Poster #7 between 10:00-12:30 in Hall B2-C and sample some jazz! With @robrombach @andi_blatt D. Lorenz @runwayml B. Ommer
    00:00
  • user avatar
    Patrick Esser
    @pess_r
    Apr 21, 2021
    braindance.py demo to run our GeoGPT models on images in the wild. Code at github.com/CompVis/geomet… Detes at arxiv.org/abs/2104.07652
    00:00
  • user avatar
    Patrick Esser
    @pess_r
    Mar 23, 2024
    wouldn't be where we are are without @EMostaque ❤️
    user avatar
    Emad
    @EMostaque
    Mar 22, 2024
    Self-sovereign AI
    66K
  • user avatar
    Patrick Esser
    @pess_r
    Feb 7, 2022
    Jumping into a thread about video inpainting @runwayml 🦘👇 1/7
    00:00
  • user avatar
    Patrick Esser
    @pess_r
    Apr 16, 2021
    Geometry-Free View Synthesis: We don't need no 3D priors. Leave them transformers unbiased! Without coding 3D transformations into the model, they learn to synthesize novel views from a single input image. arxiv.org/abs/2104.07652
    00:00
  • user avatar
    Patrick Esser
    @pess_r
    Dec 15, 2021
    Excited about ML for creative video editing? Come work with an amazing team @runwayml ! We have open positions for Research Scientists and other roles. The team is diverse and distributed all over the world with a great remote work culture. runwayml.com/about/#open-po…
    00:00
    user avatar
    Cristóbal Valenzuela
    Runway
    @c_valenzuelab
    Dec 15, 2021
    Thrilled to announce Runway’s $35M Series B led by Coatue. Content creation and video editing are being massively transformed by machine learning and the web. Excited to double down on our mission to keep reimagining how we tell stories. More here: runwayml.com/blog/runway-ra…
  • user avatar
    Patrick Esser
    @pess_r
    Jul 14, 2020
    Denoising Diffusion Probabilistic Models converted to PyTorch with Streamlit Demo github.com/pesser/pytorch… Run demo: pip install -e git+github.com/pesser/pytorch… pytorch_diffusion_demo
    00:00
  • user avatar
    Patrick Esser
    @pess_r
    Oct 13, 2021
    So many good news! 🥳 I joined @runwayml as a Research Scientist! I'll present Geometry-Free View Synthesis (arxiv.org/abs/2104.07652) at #ICCV2021 today 6 pm and Friday 11 am EDT 👋 ImageBART (arxiv.org/abs/2108.08827) was accepted at #NeurIPS2021 w/ @robrombach @andi_blatt & BO
  • user avatar
    Patrick Esser
    @pess_r
    Mar 6, 2024
    ❤️ let's gooo 🚀
    user avatar
    Robin Rombach
    @robrombach
    Mar 6, 2024
    Party time! The SD3 paper made it to arxiv: arxiv.org/abs/2403.03206 Key takeaways: - flow matching is very nice. - back to work with @pess_r and a fantastic team ♥️ The paper is full of details on improved flow matching, scaling and engineering. Enjoy!
    5.9K
  • user avatar
    Patrick Esser
    @pess_r
    Jun 17, 2024
    sooooo good! 🤩 amazing work, congrats to the whole @runwayml team!!
    user avatar
    Runway
    @runwayml
    Jun 17, 2024
    Introducing Gen-3 Alpha: Runway’s new base model for video generation. Gen-3 Alpha can create highly detailed videos with complex scene changes, a wide range of cinematic choices, and detailed art directions. runwayml.com/gen-3-alpha (1/10)
    00:00
    3.8K