Deprecated: The each() function is deprecated. This message will be suppressed on further calls in /home/zhenxiangba/zhenxiangba.com/public_html/phproxy-improved-master/index.php on line 456
Paper page - LCM-LoRA: A Universal Stable-Diffusion Acceleration Module
[go: Go Back, main page]

Librarian Bot. I found the following papers similar to this paper.

\n

The following papers were recommended by the Semantic Scholar API

\n\n

Please give a thumbs up to this comment if you found it helpful!

\n

If you want recommendations for any Paper on Hugging Face checkout this Space

\n","updatedAt":"2023-11-14T15:31:32.602Z","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":318,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.6989957690238953},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[{"reaction":"🀝","users":["victor","YYYY2023"],"count":2}],"isReport":false}},{"id":"657b763637d20b27ef4d6b2a","author":{"_id":"63dec19d10678851bb0a18eb","avatarUrl":"/avatars/668cd2c7d8fa3c3b1a3bf8ad761ab2fa.svg","fullname":"J Blu","name":"jujutechnology","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":15,"isUserFollowing":false},"createdAt":"2023-12-14T21:40:06.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"Great work! How do do keep a random seed? In the huggingface Space it stays on the last generated seed unless you manually change it. I tried -1, but that doesn't work.","html":"

Great work! How do do keep a random seed? In the huggingface Space it stays on the last generated seed unless you manually change it. I tried -1, but that doesn't work.

\n","updatedAt":"2023-12-14T21:40:06.021Z","author":{"_id":"63dec19d10678851bb0a18eb","avatarUrl":"/avatars/668cd2c7d8fa3c3b1a3bf8ad761ab2fa.svg","fullname":"J Blu","name":"jujutechnology","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":15,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.9670772552490234},"editors":["jujutechnology"],"editorAvatarUrls":["/avatars/668cd2c7d8fa3c3b1a3bf8ad761ab2fa.svg"],"reactions":[],"isReport":false}},{"id":"65b39ca82be9660f0b6577c8","createdAt":"2024-01-26T11:51:04.000Z","type":"comment","data":{"edited":true,"hidden":true,"hiddenBy":"","latest":{"raw":"This comment has been hidden","html":"This comment has been hidden","updatedAt":"2024-01-26T23:53:27.734Z"},"numEdits":0,"editors":[],"editorAvatarUrls":[],"reactions":[]}},{"id":"663dcf4b7d3a8436b9116886","createdAt":"2024-05-10T07:39:55.000Z","type":"comment","data":{"edited":true,"hidden":true,"hiddenBy":"","latest":{"raw":"This comment has been hidden","html":"This comment has been hidden","updatedAt":"2024-08-09T06:00:11.998Z"},"numEdits":0,"editors":[],"editorAvatarUrls":[],"reactions":[]}},{"id":"66656738628a6ad02e0c69b6","author":{"_id":"6186ddf6a7717cb375090c01","avatarUrl":"/avatars/716b6a7d1094c8036b2a8a7b9063e8aa.svg","fullname":"Julien BLANCHON","name":"blanchon","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":176,"isUserFollowing":false},"createdAt":"2024-06-09T08:26:32.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"# LCM-LoRA: Boosting Text-to-Image Generation Efficiency!\n\nhttps://cdn-uploads.huggingface.co/production/uploads/6186ddf6a7717cb375090c01/7-2Hi4qhDdR8fNPEuO7mW.mp4 \n\n## Links πŸ”—:\nπŸ‘‰ Subscribe: https://www.youtube.com/@Arxflix\nπŸ‘‰ Twitter: https://x.com/arxflix\nπŸ‘‰ LMNT (Partner): https://lmnt.com/\n\n\nBy Arxflix\n![9t4iCUHx_400x400-1.jpg](https://cdn-uploads.huggingface.co/production/uploads/6186ddf6a7717cb375090c01/v4S5zBurs0ouGNwYj1GEd.jpeg)","html":"

\n\t\n\t\t\n\t\n\t\n\t\tLCM-LoRA: Boosting Text-to-Image Generation Efficiency!\n\t\n

\n

\n\n

\n\t\n\t\t\n\t\n\t\n\t\tLinks πŸ”—:\n\t\n

\n

πŸ‘‰ Subscribe: https://www.youtube.com/@Arxflix
πŸ‘‰ Twitter: https://x.com/arxflix
πŸ‘‰ LMNT (Partner): https://lmnt.com/

\n

By Arxflix
\"9t4iCUHx_400x400-1.jpg\"

\n","updatedAt":"2024-06-09T08:26:32.791Z","author":{"_id":"6186ddf6a7717cb375090c01","avatarUrl":"/avatars/716b6a7d1094c8036b2a8a7b9063e8aa.svg","fullname":"Julien BLANCHON","name":"blanchon","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":176,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.4848284423351288},"editors":["blanchon"],"editorAvatarUrls":["/avatars/716b6a7d1094c8036b2a8a7b9063e8aa.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2311.05556","authors":[{"_id":"654d9b69f714720ae27e332e","user":{"_id":"652a4f174d0eef4a2bf85096","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/ofYN04WWtD60oeDP45pQN.jpeg","isPro":false,"fullname":"Simian Luo","user":"SimianLuo","type":"user"},"name":"Simian Luo","status":"admin_assigned","statusLastChangedAt":"2023-11-10T08:55:54.016Z","hidden":false},{"_id":"654d9b69f714720ae27e332f","user":{"_id":"65237947706c755148c2678b","avatarUrl":"/avatars/b7ba5dbf6286e8fa8f4f4999a473bd94.svg","isPro":true,"fullname":"Yiqin Tan","user":"tyq1024","type":"user"},"name":"Yiqin Tan","status":"admin_assigned","statusLastChangedAt":"2023-11-10T08:56:02.144Z","hidden":false},{"_id":"654d9b69f714720ae27e3330","user":{"_id":"5ec0135ded25d76864d553f1","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1600014820272-5ec0135ded25d76864d553f1.jpeg","isPro":false,"fullname":"Suraj Patil","user":"valhalla","type":"user"},"name":"Suraj Patil","status":"admin_assigned","statusLastChangedAt":"2023-11-10T09:02:32.127Z","hidden":false},{"_id":"654d9b69f714720ae27e3331","user":{"_id":"64433881f99d6629a71d39ed","avatarUrl":"/avatars/35e7257e357064e77cfdcae384afe36f.svg","isPro":false,"fullname":"Daniel Gu","user":"dg845","type":"user"},"name":"Daniel Gu","status":"admin_assigned","statusLastChangedAt":"2023-11-10T09:03:10.095Z","hidden":false},{"_id":"654d9b69f714720ae27e3332","user":{"_id":"5dfcb1aada6d0311fd3d5448","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1584435275418-5dfcb1aada6d0311fd3d5448.jpeg","isPro":false,"fullname":"Patrick von Platen","user":"patrickvonplaten","type":"user"},"name":"Patrick von Platen","status":"admin_assigned","statusLastChangedAt":"2023-11-10T08:57:29.064Z","hidden":false},{"_id":"654d9b69f714720ae27e3333","user":{"_id":"624bebf604abc7ebb01789af","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1649143001781-624bebf604abc7ebb01789af.jpeg","isPro":true,"fullname":"ApolinΓ‘rio from multimodal AI art","user":"multimodalart","type":"user"},"name":"ApolinΓ‘rio Passos","status":"admin_assigned","statusLastChangedAt":"2023-11-10T09:01:55.660Z","hidden":false},{"_id":"654d9b69f714720ae27e3334","name":"Longbo Huang","hidden":false},{"_id":"654d9b69f714720ae27e3335","user":{"_id":"63b5c13a889aa6707f0e8548","avatarUrl":"/avatars/a475b141fdc859967a9b63252620be05.svg","isPro":false,"fullname":"Jian Li","user":"jianl","type":"user"},"name":"Jian Li","status":"admin_assigned","statusLastChangedAt":"2023-11-10T09:00:08.819Z","hidden":false},{"_id":"654d9b69f714720ae27e3336","user":{"_id":"63bc8467b8c61b8aa49c3e11","avatarUrl":"/avatars/f75a33b6bba1bb6aecbe018dcef39131.svg","isPro":false,"fullname":"Hang Zhao","user":"sgzhaohang","type":"user"},"name":"Hang Zhao","status":"admin_assigned","statusLastChangedAt":"2023-11-10T09:00:17.152Z","hidden":false}],"publishedAt":"2023-11-09T18:04:15.000Z","submittedOnDailyAt":"2023-11-10T02:27:29.726Z","title":"LCM-LoRA: A Universal Stable-Diffusion Acceleration Module","submittedOnDailyBy":{"_id":"60f1abe7544c2adfd699860c","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674929746905-60f1abe7544c2adfd699860c.jpeg","isPro":false,"fullname":"AK","user":"akhaliq","type":"user"},"summary":"Latent Consistency Models (LCMs) have achieved impressive performance in\naccelerating text-to-image generative tasks, producing high-quality images with\nminimal inference steps. LCMs are distilled from pre-trained latent diffusion\nmodels (LDMs), requiring only ~32 A100 GPU training hours. This report further\nextends LCMs' potential in two aspects: First, by applying LoRA distillation to\nStable-Diffusion models including SD-V1.5, SSD-1B, and SDXL, we have expanded\nLCM's scope to larger models with significantly less memory consumption,\nachieving superior image generation quality. Second, we identify the LoRA\nparameters obtained through LCM distillation as a universal Stable-Diffusion\nacceleration module, named LCM-LoRA. LCM-LoRA can be directly plugged into\nvarious Stable-Diffusion fine-tuned models or LoRAs without training, thus\nrepresenting a universally applicable accelerator for diverse image generation\ntasks. Compared with previous numerical PF-ODE solvers such as DDIM,\nDPM-Solver, LCM-LoRA can be viewed as a plug-in neural PF-ODE solver that\npossesses strong generalization abilities. Project page:\nhttps://github.com/luosiallen/latent-consistency-model.","upvotes":87,"discussionId":"654d9b6af714720ae27e335f","githubRepo":"https://github.com/luosiallen/latent-consistency-model","githubRepoAddedBy":"auto","ai_summary":"LCMs enhance text-to-image generation by distilling from LDMs using LoRA for reduced memory and superior quality, and introduce LCM-LoRA as a plug-in accelerator for various tasks.","ai_keywords":["Latent Consistency Models","LCMs","latent diffusion models","LDMs","LoRA","Stable-Diffusion","SD-V1.5","SSD-1B","SDXL","LCM-LoRA","DDIM","DPM-Solver","plug-in neural PF-ODE solver"],"githubStars":4615},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"652a4f174d0eef4a2bf85096","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/ofYN04WWtD60oeDP45pQN.jpeg","isPro":false,"fullname":"Simian Luo","user":"SimianLuo","type":"user"},{"_id":"6039478ab3ecf716b1a5fd4d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6039478ab3ecf716b1a5fd4d/_Thy4E7taiSYBLKxEKJbT.jpeg","isPro":true,"fullname":"taesiri","user":"taesiri","type":"user"},{"_id":"620783f24e28382272337ba4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/620783f24e28382272337ba4/zkUveQPNiDfYjgGhuFErj.jpeg","isPro":false,"fullname":"GuoLiangTang","user":"Tommy930","type":"user"},{"_id":"62aaaaf55a99fb2669bcd0e3","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1655352046059-noauth.jpeg","isPro":false,"fullname":"GaggiX","user":"GaggiX","type":"user"},{"_id":"6317016f7b0ee0136e5f567d","avatarUrl":"/avatars/fe848d448318fdc17d42967b01101fea.svg","isPro":false,"fullname":"Jan Metzen","user":"jmetzen","type":"user"},{"_id":"630412d57373aacccd88af95","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1670594087059-630412d57373aacccd88af95.jpeg","isPro":true,"fullname":"Yasunori Ozaki","user":"alfredplpl","type":"user"},{"_id":"64e2d1b93e2e103504857a98","avatarUrl":"/avatars/6ed097d51aec9692972e537956e1a91a.svg","isPro":false,"fullname":"wwnz","user":"patrolli","type":"user"},{"_id":"64747f7e33192631bacd8831","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64747f7e33192631bacd8831/dstkZJ4sHJSeqLesV5cOC.jpeg","isPro":false,"fullname":"Taufiq Dwi Purnomo","user":"taufiqdp","type":"user"},{"_id":"62664b374e996ebbb6d5fef6","avatarUrl":"/avatars/8503573fb2e790b03a74d3e732442009.svg","isPro":false,"fullname":"Adel","user":"adelka","type":"user"},{"_id":"63a369d98c0c89dcae3b8329","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63a369d98c0c89dcae3b8329/AiH2zjy1cnt9OADAAZMLD.jpeg","isPro":false,"fullname":"Adina Yakefu","user":"AdinaY","type":"user"},{"_id":"64b183300a54158d66dd3587","avatarUrl":"/avatars/55ee1f1a0bf57a9d045e739f6dbbaeed.svg","isPro":false,"fullname":"Rocl Jamez","user":"James62","type":"user"},{"_id":"6427b68c682e4152bbdfba62","avatarUrl":"/avatars/d6af5f422685e0521b3a3a6030d86102.svg","isPro":false,"fullname":"Patrick Victor Gould","user":"patrickvgould","type":"user"}],"acceptLanguages":["*"],"dailyPaperRank":1}">
Papers
arxiv:2311.05556

LCM-LoRA: A Universal Stable-Diffusion Acceleration Module

Published on Nov 9, 2023
Β· Submitted by
AK
on Nov 10, 2023
#1 Paper of the day

Abstract

LCMs enhance text-to-image generation by distilling from LDMs using LoRA for reduced memory and superior quality, and introduce LCM-LoRA as a plug-in accelerator for various tasks.

AI-generated summary

Latent Consistency Models (LCMs) have achieved impressive performance in accelerating text-to-image generative tasks, producing high-quality images with minimal inference steps. LCMs are distilled from pre-trained latent diffusion models (LDMs), requiring only ~32 A100 GPU training hours. This report further extends LCMs' potential in two aspects: First, by applying LoRA distillation to Stable-Diffusion models including SD-V1.5, SSD-1B, and SDXL, we have expanded LCM's scope to larger models with significantly less memory consumption, achieving superior image generation quality. Second, we identify the LoRA parameters obtained through LCM distillation as a universal Stable-Diffusion acceleration module, named LCM-LoRA. LCM-LoRA can be directly plugged into various Stable-Diffusion fine-tuned models or LoRAs without training, thus representing a universally applicable accelerator for diverse image generation tasks. Compared with previous numerical PF-ODE solvers such as DDIM, DPM-Solver, LCM-LoRA can be viewed as a plug-in neural PF-ODE solver that possesses strong generalization abilities. Project page: https://github.com/luosiallen/latent-consistency-model.

Community

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

Great work! How do do keep a random seed? In the huggingface Space it stays on the last generated seed unless you manually change it. I tried -1, but that doesn't work.

deleted
This comment has been hidden
deleted
This comment has been hidden

LCM-LoRA: Boosting Text-to-Image Generation Efficiency!

Links πŸ”—:

πŸ‘‰ Subscribe: https://www.youtube.com/@Arxflix
πŸ‘‰ Twitter: https://x.com/arxflix
πŸ‘‰ LMNT (Partner): https://lmnt.com/

By Arxflix
9t4iCUHx_400x400-1.jpg

Sign up or log in to comment

Models citing this paper 11

Browse 11 models citing this paper

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2311.05556 in a dataset README.md to link it from this page.

Spaces citing this paper 270

Collections including this paper 34