Robin Rombach @robrombach
Generative enthusiast and long-term PhD Student @LMU_Muenchen. Author of VQGAN, Latent Diffusion, Stable Diffusion. Black Forest Joined July 2019-
Tweets337
-
Followers6K
-
Following395
-
Likes3K
Best blog of all time
⚡️SD3-Turbo: Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation Following Stable Diffusion 3, my ex-colleagues have published a preprint on SD3 distillation using 4-step, while maintaining quality. The new method – Latent Adversarial Diffusion…
Thanks for everything ♥️ Your contribution to generative AI and open source is absolutely outstanding.
Thanks for everything ♥️ Your contribution to generative AI and open source is absolutely outstanding.
Seconded, I can't thank @EMostaque enough for bringing me on at @StabilityAI. He's a real one, don't believe everything that you read.
Seconded, I can't thank @EMostaque enough for bringing me on at @StabilityAI. He's a real one, don't believe everything that you read.
wouldn't be where we are are without @EMostaque ❤️
What's better than Adversarial Diffusion Distillation (ADD)? Yes: *Latent* ADD. We turn the diffusion transformer in SD3 into a discriminator, move distillation to latent space and get SD3-Turbo, which achieves SD3's quality in only four unguided steps. >arxiv.org/abs/2403.12015
Thanks @_akhaliq We successfully turbofied SD3! SD3-Turbo achieves the sample quality of SD3, Midjourney, and Dalle-E 3 in only 4 steps. 🚀 Also, super fast editing and inpainting.
Thanks @_akhaliq We successfully turbofied SD3! SD3-Turbo achieves the sample quality of SD3, Midjourney, and Dalle-E 3 in only 4 steps. 🚀 Also, super fast editing and inpainting.
SV3D takes an image as input and outputs camera-controlled novel views that are highly consistent across the views. We also propose techniques to convert these novel views into quality 3D meshes. View synthesis models are publicly released. Project page: sv3d.github.io
SV3D takes an image as input and outputs camera-controlled novel views that are highly consistent across the views. We also propose techniques to convert these novel views into quality 3D meshes. View synthesis models are publicly released. Project page: sv3d.github.io
Today, we are releasing Stable Video 3D, a generative model based on Stable Video Diffusion. This new model advances the field of 3D technology, delivering greatly improved quality and multi-view. The model is available now for commercial and non-commercial use with a Stability…
We have now hit 330 *million* cumulative downloads since our first model was uploaded @huggingface 18 months ago. Just overtook @Google (321m all time), on our way to 1 billion thanks to the great efforts of the team @StabilityAI Some announcements to come, big weeks ahead..
We have now hit 330 *million* cumulative downloads since our first model was uploaded @huggingface 18 months ago. Just overtook @Google (321m all time), on our way to 1 billion thanks to the great efforts of the team @StabilityAI Some announcements to come, big weeks ahead..
The AI for Content Creation workshop is back at CVPR 2024 ai4cc.net Top speakers and late-breaking speakers too. Workshop papers (due Mar21st), prizes to win, even travel awards (due Mar15th)!
Happy to see that our work on diffusion model objectives (arxiv.org/abs/2303.00848) is starting to get noticed, with e.g. Stable Diffusion 3 (arxiv.org/abs/2403.03206) building on our result that the flow matching objective can be simply understood as a special case of diffusion.
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!
Highly recommended departure
Language models are overrated
The Stable Diffusion 3 paper is here 🥳 I think my colleagues have done a great job with this paper so thought I'd do a quick walk-thru thread (1/13)↓
The Stable Diffusion 3 paper is here 🥳 I think my colleagues have done a great job with this paper so thought I'd do a quick walk-thru thread (1/13)↓
The end of February brings the last blog post in the short series on score-based generative models. After score matching and SDEs, it is time for flow matching! Link to the post: jmtomczak.github.io/blog/18/18_fm.… Link to the code: github.com/jmtomczak/intr…
AK @_akhaliq
310K Followers 3K Following AI research paper tweets, ML @Gradio (acq. by @HuggingFace 🤗) dm for promo follow on Hugging Face: https://t.co/q2Qoey80GxAndrej Karpathy @karpathy
979K Followers 905 Following 🧑🍳. Previously Director of AI @ Tesla, founding team @ OpenAI, CS231n/PhD @ Stanford. I like to train large deep neural nets 🧠🤖💥Stability AI @StabilityAI
190K Followers 31 Following We are building the foundation to activate humanity's potential.Jim Fan @DrJimFan
229K Followers 3K Following @NVIDIA Sr. Research Manager & Lead of Embodied AI (GEAR Lab). Creating foundation models for Humanoid Robots & Gaming. @Stanford Ph.D. @OpenAI's first intern.Rivers Have Wings @RiversHaveWings
31K Followers 224 Following AI/generative artist. Writes her own code. Absolute power is a door into dreaming.Stable Diffusion 🎨.. @DiffusionPics
59K Followers 41 Following Stable Diffusion powered Generative AI Art 🖼️ Animation 🎞 & Research 🧪 by #StabilityAI 🤖 AI image generation #SDXL #ControlNet #AnimateDiff (Midjourney)AI Pub @ai__pub
72K Followers 343 Following AI papers and AI research explained, for technical people. Get hired by the best AI companies: https://t.co/MySVjUGOQ3Stable Foundation @StableDiffusion
65K Followers 181 Following Stable Digest #13 out now! link in bio ⬇️ #StableDiffusion — AI by the people, for the people. (っ◔◡◔)っ ♥ @StabilityAI communityKaliYuga @KaliYuga_ai
27K Followers 809 Following Like dust, magic gathers in overlooked places | she/her | ✡️ | #Aiart since 2020 | @StabilityAi | Opinions are my ownJustin Pinkney @Buntworthy
10K Followers 1K Following Playing with deep learning, computer vision and generative art. Co-creator of https://t.co/sYtHB9e5Dj, ML Researcher @ MidJourney @[email protected]TomLikesRobots🤖 @TomLikesRobots
33K Followers 5K Following AI Artist at Metaphysic working with AI and VFX. All views my own. Experienced Web Dev and Artist. Early explorer of Artificial Creativity.Sharif Shameem @sharifshameem
53K Followers 3K Following founder @LexicaArt • in pursuit of good explanationsGuy Parsons @GuyP
51K Followers 7K Following building things with #AI 🤖 #DALLE & #MidJourney adventurer ✍️ editor, https://t.co/77MJXuLSTd 🖼 curator of the https://t.co/8Xctk6XoPsRoope Rainisto @rainisto
34K Followers 2K Following Artist behind “Life In West America”, "Reworld" and "Smile" NFT collections. WME represented. Designer, creator, photographer, screenwriter, endless learner.Emm @emmanuel_2m
32K Followers 6K Following Co-founder & CEO at https://t.co/7ElrGjg10n 🚀 | Craft unique and style-consistent game assets with custom-trained AI models 👾 | #GenAI #Gaming @scenario_ggJeremy Howard @jeremyphoward
222K Followers 5K Following 🇦🇺 Co-founder: @AnswerDotAI & @FastDotAI ; Hon Professor: @UQSchoolITEE ; Digital Fellow: @StanfordTanishq Mathew Abraha.. @iScienceLuvr
54K Followers 1K Following PhD at 19 | Founder and CEO at @MedARC_AI | Research Director at @StabilityAI | @kaggle Notebooks GM | Biomed. engineer @ 14 | TEDx talk➡https://t.co/xPxwKTq6QbSander Dieleman @sedielem
50K Followers 2K Following Research Scientist at Google DeepMind. I tweet about deep learning (research + software), music, generative models (personal account).Mario Klingemann💧�.. @quasimondo
58K Followers 2K Following Artist, Neurographer, AI Prompteur, Purveyor of Systems, Data Dumpster Diver, Information RecyclerMing Huang @xwe23sfa
0 Followers 3 FollowingMichael Molin @thematrixcom
1K Followers 2K Following General Intelligence System - https://t.co/56AXhKlqhq - Deep explorationForsad Al Hossain @forsadalhossain
117 Followers 593 Following CICS Ph.D. student at Umass Amherst; did Competitive Programming and DSP research, wrote C++ software, and now working on novel usage of AI in the real worldLedell Wu @LedellWu
698 Followers 247 Following AI Research Scientist (Generative AI/LLM/Multimodal) Co-founder @CreatifyLab, Past: FAIR @MetaAI, @BAAIBeijing Recipient of ICML 2023 Test-of-Time AwardJustus Bruns @justusbruns
1 Followers 92 FollowingAnkit @ashah0052
1K Followers 5K Following LLM Arch Assoc Director - @Accenture Ph.D. - @LTIatCMU @SCSatCMU Previous: @GoogleAI, @merl_news, @Revive_Med, @ARM Smartly working hard to make things happen!Jiawei Yang @JiaweiYang118
246 Followers 219 Following USC PhD student | Student Researcher@Google Researcher | ex-Intern @ Nvidia ResearchDonald Chen @donydchen
38 Followers 59 Following PhD student @MonashUni | Working on 3D Computer Vision | Views are his own.Mark Bentsen @MarkBentsen
129 Followers 563 Following Dallas, Texas; wife of 22 years and two teenagers that help us maintain a continuous learning mindset. Yes, I waited 7hrs in line for the first iPhone.SUSCITATION @suscitation
4K Followers 2K FollowingPrabhat Kumar Singh @prab_at
277 Followers 42 Following Building Knowledge Graphs for AI CEO of @Cyberiums Born in Bihar. Native of Nalanda. Went to IIT. Built Apps, Tech & Great Friends.Swati @swatiardeshna
26 Followers 5K FollowingNATARAJAN MUTHU | LON.. @natarajan_muthu
41 Followers 796 Following Network Consultant | Blogger | Network Automation EngineerStefan Bachhofner @fcbstef
194 Followers 3K FollowingMartin Shkreli (e/acc.. @MartinShkreli
168K Followers 3K Following https://t.co/lzin5ByH0t [email protected] https://t.co/oMIiyJcIzk https://t.co/DuU6MMqcgQSachin Kamath @DesigningFlow
2K Followers 1K Following Artist/ Gen AI Trainer - 5000+ creative pros upskilled Building AI Lemon Academy to empower creatives with skill readiness to learn, practice and master AI.Ellis Brown @_ellisbrown
357 Followers 939 Following CS PhD Student @NYU_Courant | Prev: @CarnegieMellon, https://t.co/EkTzprGc4i, @VanderbiltUFco. Jesús Martínez.. @pakitochus
2K Followers 1K Following Postdoc Ramón y Cajal @CanalUGR @dasci_es, ciencia, música, tecnología, software libre. Instructor @thecarpentries. Barbero sientífico @barbersscienceKolja Bauer @KoljaBauer
3 Followers 27 FollowingZhaoyang Wang @wangwan83764204
316 Followers 4K Following CS PhD student at Uni of Birmingham in the United Kingdom. Research interests: Automated Machine Learning, Online Learning, and Reinforcement Learning 🏳️🌈Andy Walker @AndyWalkerAI
42 Followers 167 Following Combining different forms of AI art with the help of Python, ChatGPT, and some soul searching (Photoshop filters).CompoSecure @CompoSecure
2K Followers 3K Following CompoSecure, Inc. (Nasdaq: CMPO) is a leader in metal payment cards, security, and authentication solutions.Prem Akkaraju @premakkaraju
465 Followers 61 Following Board member of Weta Digital, SR Labs, Aircore. Executive Producer of THE WHITE TIGERJames C. Wu @james_c_wu
273 Followers 224 Following AI/ML & Infrastructure Investor @FirstRound. Previously led ML @Amperity, Co-founder/CEO AdaptiLab (acquired by @CoderPad).Ramin Hasani @ramin_m_h
3K Followers 258 Following Cofounder & CEO https://t.co/fh9fnDA9OQ | ML Researcher @ MITKamyar Ghasemipour @coolboi95
867 Followers 2K Following ML grad student at U of T / Vector Institute. I go by Kamyar. Currently affiliated with Google Robotics. He/Him.MrlolDev @MrlolDev
178 Followers 1K Following I am leo web dev fullstack Teenager finishing high school EX-CEO of @Turing_AI_ Working at @get_wildfireAlexander Swerdlow @alexjswerdlow
9 Followers 196 FollowingHyperBooth AI @HyperBooth_AI
185 Followers 401 Following https://t.co/KT7lFdBEyg is a Generative AI image tool. Create stunning AI photos instantly with just one selfie with #hyperboothai.munshi memechand @MaalDakhni
78 Followers 2K Following 21 | writes @kulliyaat | aspiring statistikdoktor | kullback leibler neurodivergence | shafiiOfir Press 🖋 @OfirPress
10K Followers 3K Following I build tough benchmarks for LMs and then I get the LMs to solve them. Postdoc @Princeton. PhD from @nlpnoah @UW. Ex-visiting researcher @MetaAI & @MosaicML.Ramin Hamedi @HamediRamin
56 Followers 2K Followingthreeaus @threeaus
77 Followers 1K Followingwoodman @woodman83294792
215 Followers 2K FollowingZZT-VC @zzt2024
108 Followers 337 Following father| husband| reader| thinker| Shopify early investorNikita @nikitavoloboev
4K Followers 7K Following Make @LearnAnything_ Learn in public: https://t.co/GbFvuErkYn macOS course: https://t.co/JdbJWru6zG https://t.co/94R8ER7K2h https://t.co/ROkqhyhpEKCryptonymics🍎🚀 @cryptonymics
207 Followers 407 Following the world was boring until 2012 🍎🚀 builder of ideas加藤 豪 @_5925263769112
264 Followers 30 Following 1964年生まれ。美術家。【学歴】東京芸術大学絵画科油画専攻卒業。東京芸術大学大学院美術研究科修了。【主な展覧会】2008年、釜山ビエンナーレ(釜山市立美術館)。2001年、先立未来展(ルイジ・ペッチ美術館、イタリア)。1997年、デ・ジェンダリズム展(世田谷美術館)。名古屋市在住。https://t.co/6ib2iK1tdtasp @underfitai
8 Followers 99 FollowingAK @_akhaliq
310K Followers 3K Following AI research paper tweets, ML @Gradio (acq. by @HuggingFace 🤗) dm for promo follow on Hugging Face: https://t.co/q2Qoey80GxAndrej Karpathy @karpathy
979K Followers 905 Following 🧑🍳. Previously Director of AI @ Tesla, founding team @ OpenAI, CS231n/PhD @ Stanford. I like to train large deep neural nets 🧠🤖💥Yann LeCun @ylecun
712K Followers 719 Following Professor at NYU. Chief AI Scientist at Meta. Researcher in AI, Machine Learning, Robotics, etc. ACM Turing Award Laureate.Stability AI @StabilityAI
190K Followers 31 Following We are building the foundation to activate humanity's potential.Rivers Have Wings @RiversHaveWings
31K Followers 224 Following AI/generative artist. Writes her own code. Absolute power is a door into dreaming.Lucas Beyer (bl16) @giffmana
56K Followers 446 Following Researcher (Google DeepMind/Brain in Zürich, ex-RWTH Aachen), Gamer, Hacker, Belgian. Mostly gave up trying mastodon as [email protected]Stable Foundation @StableDiffusion
65K Followers 181 Following Stable Digest #13 out now! link in bio ⬇️ #StableDiffusion — AI by the people, for the people. (っ◔◡◔)っ ♥ @StabilityAI communityKaliYuga @KaliYuga_ai
27K Followers 809 Following Like dust, magic gathers in overlooked places | she/her | ✡️ | #Aiart since 2020 | @StabilityAi | Opinions are my ownJustin Pinkney @Buntworthy
10K Followers 1K Following Playing with deep learning, computer vision and generative art. Co-creator of https://t.co/sYtHB9e5Dj, ML Researcher @ MidJourney @[email protected]TomLikesRobots🤖 @TomLikesRobots
33K Followers 5K Following AI Artist at Metaphysic working with AI and VFX. All views my own. Experienced Web Dev and Artist. Early explorer of Artificial Creativity.AI at Meta @AIatMeta
532K Followers 255 Following Together with the AI community, we are pushing the boundaries of what’s possible through open science to create a more connected world.Sharif Shameem @sharifshameem
53K Followers 3K Following founder @LexicaArt • in pursuit of good explanationsHugging Face @huggingface
345K Followers 189 Following The AI community building the future. https://t.co/VkRPD0VKaZ #BlackLivesMatter #stopasianhateRoope Rainisto @rainisto
34K Followers 2K Following Artist behind “Life In West America”, "Reworld" and "Smile" NFT collections. WME represented. Designer, creator, photographer, screenwriter, endless learner.Jeremy Howard @jeremyphoward
222K Followers 5K Following 🇦🇺 Co-founder: @AnswerDotAI & @FastDotAI ; Hon Professor: @UQSchoolITEE ; Digital Fellow: @StanfordTanishq Mathew Abraha.. @iScienceLuvr
54K Followers 1K Following PhD at 19 | Founder and CEO at @MedARC_AI | Research Director at @StabilityAI | @kaggle Notebooks GM | Biomed. engineer @ 14 | TEDx talk➡https://t.co/xPxwKTq6QbSander Dieleman @sedielem
50K Followers 2K Following Research Scientist at Google DeepMind. I tweet about deep learning (research + software), music, generative models (personal account).community notes viola.. @cnviolations
865K Followers 6 Following not affiliated with @x or @communitynotes | DM SubmissionsPrem Akkaraju @premakkaraju
465 Followers 61 Following Board member of Weta Digital, SR Labs, Aircore. Executive Producer of THE WHITE TIGERJennifer Li @JenniferHli
6K Followers 1K Following General Partner @a16z Infra. 💙 product, data and dev tools. (Profile photo by @ideogram_ai)Ahmad Al-Dahle @Ahmad_Al_Dahle
4K Followers 53 Following #Girldad of twins. Leading GenAI @ Meta (llama, imagine, meta ai and more)Jon Oringer @jonoringer
28K Followers 1K Following Founder & Executive Chairman @Shutterstock — always bootstrappingLina Colucci, PhD @lina_colucci
6K Followers 1K Following Co-Founder @toinfinityai (YC W24). Try it here: https://t.co/U3BKdJLVqN. 2x Founder. Alum: @MIT @Harvard @DukeU 🇧🇷→🇨🇦→🇺🇸udio @udiomusic
28K Followers 0 FollowingAaron Defazio @aaron_defazio
6K Followers 364 Following Research Scientist at Meta working on optimization. Fundamental AI Research (FAIR) teamLykon @Lykon4072
2K Followers 16 FollowingxAI @xai
997K Followers 36 FollowingKevin Patrick Murphy @sirbayes
42K Followers 334 Following Research Scientist at Google Brain / Deepmind. Interested in Bayesian Machine Learning.Flowers from the futu.. @futuristflower
13K Followers 114 Following In the unity of all, under night's solemn sky, she stands, sacred and forlorn, with a cunty gleam in her eye.Mariya I. Vasileva @mariyaivasileva
5K Followers 1K Following All things computer vision + generative AI • ex @AWS, @KaiberAI • 🎓@IllinoisCS (PhD), @Caltech • Organizer @WiMLWorkshop, @CVFADworkshop, @ResistanceAI • 🇧🇬Gregor von Dulong @gregorvondulong
56 Followers 135 Following Weekly Newsletter About ML Research And The Data Economy (https://t.co/EuxsoYIRyX) | ML EngineerArthur Mensch @arthurmensch
40K Followers 873 Following Co-founder and CEO @MistralAI. Apply https://t.co/yHGRZAtjcxTali Dekel @talidekel
2K Followers 286 Following Assistant Professor @ Weizmann Institute; Research Scientist @ GoogleFireworks AI @FireworksAI_HQ
5K Followers 65 Following 🎆 Generative AI Platform built for developersCyril Diagne @cyrildiagne
27K Followers 1K Following AI indie hacker - Prev: co-founder & ceo @clipdropapp (YC W21, acq. by @StabilityAI), resident @googlearts, prof & head @ecal_midRajko Radovanović @rajko_rad
4K Followers 4K Following AI/infra @a16z (partner to amazing teams eg @MistralAI @udiomusic); Enjoy most things outdoors, care about democracy in 🇷🇸🇭🇷🇸🇮🇧🇦🇲🇪main @main_horse
8K Followers 477 Following AGI Believer. Haven't applied @OpenAI. Likes are not always endorsement.martin_casado @martin_casado
50K Followers 2K Following GP @ a16z ... questionable heuristics in a grossly underdetermined worldEric Hartford @erhartford
12K Followers 399 Following Principal Applied AI Researcher @TensorWaveCloud I make AI models Dolphin and Samantha https://t.co/3ri2GbXrQB BTC 3ENBV6zdwyqieAXzZP2i3EjeZtVwEmAuo4Trevor Loy @trevorloy
17K Followers 2K Following VC investor emerging ecosystems @FlywheelVC. Lecturer entrepreneurship & VC @Stanford. Prev: BoD @NVCA; Mentor @KauffmanFellows; 3x founder; Chip design @Intel.Bas Veeling @BasVeeling
1K Followers 986 Following K’Nex’ing molecules at Microsoft Research. Previously student researcher at Google Brain and PhD student at AMLab.Together AI @togethercompute
27K Followers 304 Following The future of AI is open-source. Let's build together.amit ⚡️ @gravicle
7K Followers 4K Following ceo @LumaLabsAI | prev: built Vision Pro at | everything is figureoutableAutopilot ♟ @JoinAutopilot_
57K Followers 166 Following Rebuilding trust in our financial institutions, starting w/ the PoliticiansShahbuland Matiana - .. @shah_bu_land
370 Followers 171 Following Co-Founder @carperai and researcher at @stabilityai prev @uwaterloo I want to make AI generated video gamesTeknium (e/λ) @Teknium1
29K Followers 3K Following Cofounder @NousResearch, prev @StabilityAI Github: https://t.co/LZwHTUFwPq HuggingFace: https://t.co/sN2FFU8PVE Support me on Github SponsorsSimon Kohl @saakohl
1K Followers 416 Following ML for Biology. ex-DeepMinder, AlphaFold2 core team member and initiative co-lead in the DeepMind science team. Working on something new.Justine Moore @venturetwins
56K Followers 890 Following Partner @a16z investing in all things AI 🤖 | Twin to @omooretweetsBahjat Kawar @bahjat_kawar
453 Followers 180 Following PhD from @TechnionLive. Machine Learning & Computer Vision Researcher @Apple. Interested in Diffusion Models.Michael Tschannen @mtschannen
1K Followers 618 Following Machine learning researcher @GoogleDeepMind. Past: @Apple, @awscloud AI, @ETH_en. Multimodal/representation learning.Ben Mildenhall @BenMildenhall
5K Followers 992 Following making stuff 3D. formerly research scientist at Google, phd at Berkeley.Ruiqi Gao @RuiqiGao
5K Followers 511 Following Research scientist @Google DeepMind. Generative modeling, representation learning.Aishwarya Kamath @ashkamath20
7K Followers 587 Following Research Scientist @GoogleDeepMind. PhD at NYULots of anxiety about SB 1047 in CA, and a lot of swirl. The broad contours will be familiar to folks following the US Executive Order and EU AI Act. There's a line in the sand, and if you cross the line, you have to do and disclose a bunch of things before training and releasing…
California Bill 1047 has been fasttracked: • Covers all models made w/ 10^26 flops • Covers all models with similar perf to above • Creates a Frontier Model Division to report to • Devs must assert such models are safe under penalty of perjury text: legiscan.com/CA/text/SB1047…
What a fucking disaster. California Bill 1047 is an attack on AI innovation. It has much of the bullshit often found in these bills (kill switch, certification, criminal penalties). It will hurt researchers, academics, & startups. legiscan.com/CA/text/SB1047…
In the era of #GenerativeAI, it is time to talk about GenAI systems. What are the components of GenAI Systems (GenAISys)? Does the future of AI rely on GenAISys (e.g., agentic AI 🤖)? If you are interested, I'm happy to share my thoughts with you: jmtomczak.github.io/blog/21/21_gen… ✨
The @PyTorch team is developing a library for large model training called torchtitan 👀 They have scripts to train Llama-3 from scratch The library went public today on GitHub but it is still in pre-release state & active development Check it out → github.com/pytorch/torcht…
📢📢Most diffusion (and flow matching) models use handcrafted schedules for their denoising steps during sampling. We show how to optimize them in a principled manner for high-quality generation! @amsabour added quickstart guide & collab to get you started quickly (links below)!
📢📢 Align Your Steps: Optimizing Sampling Schedules in Diffusion Models research.nvidia.com/labs/toronto-a… TL;DR: We introduce a method for obtaining improved sampling schedules for diffusion models, resulting in better samples at the same computation cost. (1/5)
24. April, und noch mal frischer #Schnee.
ByteDance presents Hyper-SD Achieves SOTA performance from 1 to 8 inference steps for both SDXL and SD1.5 proj: hyper-sd.github.io abs: arxiv.org/abs/2404.13686
How can one easily teach caption-pretrained VLMs to localize objects? We show that a small Positional Insert (PIN) can unlock object localization abilities without annotated data on frozen autoregressive VLMs. #CVPR2024 📝: arxiv.org/abs/2402.08657 🌐: quva-lab.github.io/PIN/
Llama3-70B has settled at #5. With 405B still to come next... I remember when GPT-4 released in March 2023, it looked like it was nearly-impossible to get to the same performance. Since then, I've seen @Ahmad_Al_Dahle and the rest of the GenAI org in a chaotic rise to focus,…
Exciting update -- Llama-3 full result is out, now reaching top-5 on the Arena leaderboard🔥 We've got stable enough CIs with over 12K votes. No question now Llama-3 70B is the new king of open model. Its powerful 8B variant has also surpassed many larger-size models. What an…
Was woken up at 3h35 thinking @OpenAI had released GPT-5
@arpitingle oh my god blast from the past 😂 maybe one day i shall do a re-write of this project. i am imagining efficient, batched training + inference running the brain of all the little bots...
So very excited for the promotion of @JenniferHli to GP. She's a primary reason @a16z enterprise investing is what it is, being a key player behind so many deals, our team and our investment philosophy and process. She really is "the best of us". a16z.com/jennifer-li/
Can't wait to see multimodal LLama 3! We released a resource that might come in handy: The Cauldron🍯 The Cauldron is a massive manually-curated collection of 50 vision-language sets for instruction fine-tuning. 3.6M images, 30.3M query/answer pairs. It covers a large…
Forget the US Executive Order — 9e24 FLOPs means Llama 3-70B is on the verge of crossing the EU threshold for a systemic risk model (1e25). That would mean mandatory pre-release & post-release requirements that may be very difficult to reconcile with open release. Not only that,…
The model card has some more interesting info too: github.com/meta-llama/lla… Note that Llama 3 8B is actually somewhere in the territory of Llama 2 70B, depending on where you look. This might seem confusing at first but note that the former was trained for 15T tokens, while the…
Happy to announce Imagine Flash, which is a real-time image synthesis! Watch in real time as the image evolves with each character you type! I'm proud to be leading the Flash project with my teammates - it's incredibly rewarding to witness the transformation of a quick demo I…
Congrats to @AIatMeta on Llama 3 release!! 🎉 ai.meta.com/blog/meta-llam… Notes: Releasing 8B and 70B (both base and finetuned) models, strong-performing in their model class (but we'll see when the rankings come in @ @lmsysorg :)) 400B is still training, but already encroaching…