Hugging Face Hub · 27 vision pipeline tags in 8 fields

The State of Open Source Vision

103,703 open vision models, plus 124K in generation
49K added in the last 12 months
1.7× the 12 months before that
8 fields, from 124K models to 1K
74% of 30-day downloads go to transformers repos

as of 2026-10-01 · figures above leave out generation (124K repos, 0.56× in 12 months), the charts below include it

What open vision is made of

Every public model repo carrying one of the 27 vision tags. Pick a field here or in the bar above to follow it through the rest of the page. Fine view splits the cards, library bars and table into single tags.

New models per month, by field

Stacked, so the column height is all of open vision and each band is one field. Generation sets the scale; the fields moving fastest are underneath it.

03,0006,0009,00012,0002023202420252026Apr 2022Generation52Vision-language12Classification71Detection6Embeddings6Segmentation10Video classification0Depth & pose0all vision157May 2022Generation6Vision-language2Classification62Detection4Embeddings1Segmentation13Video classification0Depth & pose1all vision89Jun 2022Generation6Vision-language5Classification100Detection5Embeddings0Segmentation5Video classification0Depth & pose0all vision121Jul 2022Generation18Vision-language27Classification129Detection14Embeddings4Segmentation4Video classification2Depth & pose0all vision198Aug 2022Generation13Vision-language31Classification70Detection3Embeddings11Segmentation4Video classification9Depth & pose0all vision141Sep 2022Generation91Vision-language48Classification105Detection6Embeddings12Segmentation5Video classification17Depth & pose0all vision284Oct 2022Generation200Vision-language31Classification115Detection11Embeddings4Segmentation2Video classification6Depth & pose0all vision369Nov 2022Generation514Vision-language81Classification143Detection4Embeddings10Segmentation17Video classification7Depth & pose6all vision782Dec 2022Generation926Vision-language43Classification395Detection41Embeddings13Segmentation6Video classification11Depth & pose1all vision1,436Jan 2023Generation1,016Vision-language57Classification275Detection81Embeddings18Segmentation59Video classification17Depth & pose1all vision1,524Feb 2023Generation751Vision-language69Classification276Detection34Embeddings11Segmentation8Video classification12Depth & pose1all vision1,162Mar 2023Generation818Vision-language83Classification524Detection85Embeddings61Segmentation16Video classification17Depth & pose2all vision1,606Apr 2023Generation838Vision-language127Classification707Detection53Embeddings38Segmentation22Video classification17Depth & pose3all vision1,805May 2023Generation973Vision-language191Classification412Detection46Embeddings38Segmentation20Video classification41Depth & pose8all vision1,729Jun 2023Generation816Vision-language162Classification391Detection63Embeddings23Segmentation13Video classification32Depth & pose11all vision1,511Jul 2023Generation1,322Vision-language174Classification481Detection79Embeddings13Segmentation24Video classification36Depth & pose1all vision2,130Aug 2023Generation2,619Vision-language213Classification491Detection100Embeddings15Segmentation13Video classification26Depth & pose2all vision3,479Sep 2023Generation1,976Vision-language191Classification475Detection126Embeddings22Segmentation24Video classification57Depth & pose3all vision2,874Oct 2023Generation1,229Vision-language241Classification499Detection295Embeddings45Segmentation26Video classification48Depth & pose5all vision2,388Nov 2023Generation1,903Vision-language261Classification1,010Detection133Embeddings20Segmentation29Video classification51Depth & pose10all vision3,417Dec 2023Generation1,993Vision-language297Classification1,301Detection79Embeddings34Segmentation55Video classification69Depth & pose4all vision3,832Jan 2024Generation1,720Vision-language268Classification481Detection87Embeddings50Segmentation41Video classification41Depth & pose13all vision2,701Feb 2024Generation1,789Vision-language277Classification586Detection105Embeddings32Segmentation113Video classification87Depth & pose5all vision2,994Mar 2024Generation1,606Vision-language387Classification584Detection86Embeddings62Segmentation87Video classification106Depth & pose4all vision2,922Apr 2024Generation1,279Vision-language483Classification662Detection203Embeddings40Segmentation31Video classification85Depth & pose12all vision2,795May 2024Generation1,718Vision-language569Classification1,099Detection195Embeddings59Segmentation53Video classification128Depth & pose5all vision3,826Jun 2024Generation1,671Vision-language490Classification828Detection193Embeddings79Segmentation47Video classification64Depth & pose17all vision3,389Jul 2024Generation1,804Vision-language463Classification466Detection136Embeddings67Segmentation76Video classification106Depth & pose13all vision3,131Aug 2024Generation4,235Vision-language564Classification186Detection179Embeddings92Segmentation77Video classification20Depth & pose7all vision5,360Sep 2024Generation4,685Vision-language879Classification347Detection77Embeddings40Segmentation101Video classification19Depth & pose30all vision6,178Oct 2024Generation4,302Vision-language999Classification607Detection132Embeddings64Segmentation51Video classification23Depth & pose18all vision6,196Nov 2024Generation4,570Vision-language1,705Classification439Detection111Embeddings60Segmentation49Video classification60Depth & pose11all vision7,005Dec 2024Generation4,564Vision-language1,243Classification2,340Detection88Embeddings165Segmentation64Video classification56Depth & pose15all vision8,535Jan 2025Generation5,445Vision-language1,354Classification415Detection107Embeddings43Segmentation49Video classification66Depth & pose18all vision7,497Feb 2025Generation5,777Vision-language940Classification422Detection95Embeddings148Segmentation36Video classification68Depth & pose8all vision7,494Mar 2025Generation6,492Vision-language1,429Classification1,917Detection127Embeddings45Segmentation124Video classification43Depth & pose10all vision10,187Apr 2025Generation4,659Vision-language1,250Classification963Detection162Embeddings59Segmentation73Video classification47Depth & pose7all vision7,220May 2025Generation4,026Vision-language1,143Classification665Detection110Embeddings92Segmentation127Video classification94Depth & pose4all vision6,261Jun 2025Generation3,994Vision-language1,147Classification610Detection116Embeddings70Segmentation288Video classification58Depth & pose10all vision6,293Jul 2025Generation3,136Vision-language1,500Classification305Detection79Embeddings74Segmentation69Video classification21Depth & pose2all vision5,186Aug 2025Generation4,877Vision-language1,174Classification324Detection62Embeddings72Segmentation52Video classification52Depth & pose17all vision6,630Sep 2025Generation2,818Vision-language1,296Classification357Detection99Embeddings92Segmentation64Video classification45Depth & pose11all vision4,782Oct 2025Generation2,290Vision-language1,558Classification846Detection230Embeddings51Segmentation75Video classification17Depth & pose10all vision5,077Nov 2025Generation1,230Vision-language1,799Classification302Detection82Embeddings86Segmentation62Video classification171Depth & pose16all vision3,748Dec 2025Generation1,306Vision-language1,608Classification370Detection119Embeddings70Segmentation75Video classification34Depth & pose31all vision3,613Jan 2026Generation1,464Vision-language3,571Classification285Detection141Embeddings73Segmentation62Video classification18Depth & pose70all vision5,684Feb 2026Generation1,636Vision-language1,300Classification685Detection195Embeddings76Segmentation99Video classification8Depth & pose92all vision4,091Mar 2026Generation2,204Vision-language2,305Classification441Detection243Embeddings337Segmentation152Video classification27Depth & pose60all vision5,769Apr 2026Generation1,851Vision-language4,232Classification558Detection285Embeddings151Segmentation110Video classification20Depth & pose58all vision7,265May 2026Generation4,411Vision-language3,053Classification523Detection303Embeddings159Segmentation183Video classification29Depth & pose50all vision8,711Jun 2026Generation7,100Vision-language3,064Classification416Detection331Embeddings508Segmentation153Video classification33Depth & pose72all vision11,677Jul 2026Generation2,024Vision-language3,242Classification623Detection322Embeddings192Segmentation331Video classification37Depth & pose66all vision6,837Aug 2026Generation2,302Vision-language4,652Classification637Detection482Embeddings156Segmentation219Video classification38Depth & pose94all vision8,580Sep 2026Generation2,944Vision-language3,914Classification707Detection418Embeddings157Segmentation228Video classification29Depth & pose102all vision8,499Oct 2026Generation47Vision-language59Classification3Detection2Embeddings3Segmentation4Video classification0Depth & pose1all vision119

Fine view: pick a field above to split this chart into its tags.

text-to-image 111Kimage-to-image 3.9Kunconditional-image-generation 2.8Ktext-to-video 2.8Kimage-to-video 1.7Kimage-to-3d 772image-text-to-image 5603 smaller tags 804
02,0004,0006,0008,0002023202420252026Apr 2022text-to-image2image-to-image11unconditional-image-generation39text-to-video0image-to-video0image-to-3d0image-text-to-image03 smaller tags0all generation52May 2022text-to-image0image-to-image4unconditional-image-generation2text-to-video0image-to-video0image-to-3d0image-text-to-image03 smaller tags0all generation6Jun 2022text-to-image2image-to-image0unconditional-image-generation4text-to-video0image-to-video0image-to-3d0image-text-to-image03 smaller tags0all generation6Jul 2022text-to-image3image-to-image1unconditional-image-generation14text-to-video0image-to-video0image-to-3d0image-text-to-image03 smaller tags0all generation18Aug 2022text-to-image12image-to-image0unconditional-image-generation1text-to-video0image-to-video0image-to-3d0image-text-to-image03 smaller tags0all generation13Sep 2022text-to-image88image-to-image3unconditional-image-generation0text-to-video0image-to-video0image-to-3d0image-text-to-image03 smaller tags0all generation91Oct 2022text-to-image187image-to-image13unconditional-image-generation0text-to-video0image-to-video0image-to-3d0image-text-to-image03 smaller tags0all generation200Nov 2022text-to-image443image-to-image1unconditional-image-generation70text-to-video0image-to-video0image-to-3d0image-text-to-image03 smaller tags0all generation514Dec 2022text-to-image707image-to-image10unconditional-image-generation209text-to-video0image-to-video0image-to-3d0image-text-to-image03 smaller tags0all generation926Jan 2023text-to-image925image-to-image5unconditional-image-generation86text-to-video0image-to-video0image-to-3d0image-text-to-image03 smaller tags0all generation1,016Feb 2023text-to-image677image-to-image14unconditional-image-generation58text-to-video2image-to-video0image-to-3d0image-text-to-image03 smaller tags0all generation751Mar 2023text-to-image749image-to-image11unconditional-image-generation48text-to-video9image-to-video0image-to-3d1image-text-to-image03 smaller tags0all generation818Apr 2023text-to-image732image-to-image40unconditional-image-generation59text-to-video7image-to-video0image-to-3d0image-text-to-image03 smaller tags0all generation838May 2023text-to-image891image-to-image30unconditional-image-generation43text-to-video9image-to-video0image-to-3d0image-text-to-image03 smaller tags0all generation973Jun 2023text-to-image765image-to-image20unconditional-image-generation23text-to-video5image-to-video0image-to-3d0image-text-to-image03 smaller tags3all generation816Jul 2023text-to-image1,251image-to-image27unconditional-image-generation39text-to-video1image-to-video0image-to-3d0image-text-to-image03 smaller tags4all generation1,322Aug 2023text-to-image2,555image-to-image14unconditional-image-generation44text-to-video6image-to-video0image-to-3d0image-text-to-image03 smaller tags0all generation2,619Sep 2023text-to-image1,916image-to-image20unconditional-image-generation36text-to-video3image-to-video0image-to-3d0image-text-to-image03 smaller tags1all generation1,976Oct 2023text-to-image1,110image-to-image13unconditional-image-generation93text-to-video12image-to-video0image-to-3d0image-text-to-image03 smaller tags1all generation1,229Nov 2023text-to-image1,816image-to-image14unconditional-image-generation53text-to-video15image-to-video3image-to-3d2image-text-to-image03 smaller tags0all generation1,903Dec 2023text-to-image1,921image-to-image17unconditional-image-generation39text-to-video5image-to-video7image-to-3d1image-text-to-image03 smaller tags3all generation1,993Jan 2024text-to-image1,647image-to-image21unconditional-image-generation33text-to-video4image-to-video0image-to-3d10image-text-to-image03 smaller tags5all generation1,720Feb 2024text-to-image1,730image-to-image30unconditional-image-generation13text-to-video5image-to-video4image-to-3d4image-text-to-image03 smaller tags3all generation1,789Mar 2024text-to-image1,507image-to-image27unconditional-image-generation46text-to-video6image-to-video5image-to-3d13image-text-to-image03 smaller tags2all generation1,606Apr 2024text-to-image1,181image-to-image27unconditional-image-generation49text-to-video10image-to-video1image-to-3d8image-text-to-image13 smaller tags2all generation1,279May 2024text-to-image1,588image-to-image25unconditional-image-generation90text-to-video4image-to-video0image-to-3d8image-text-to-image03 smaller tags3all generation1,718Jun 2024text-to-image1,555image-to-image24unconditional-image-generation65text-to-video6image-to-video6image-to-3d10image-text-to-image03 smaller tags5all generation1,671Jul 2024text-to-image1,665image-to-image24unconditional-image-generation80text-to-video8image-to-video2image-to-3d25image-text-to-image03 smaller tags0all generation1,804Aug 2024text-to-image4,101image-to-image35unconditional-image-generation67text-to-video6image-to-video3image-to-3d23image-text-to-image03 smaller tags0all generation4,235Sep 2024text-to-image4,556image-to-image47unconditional-image-generation48text-to-video14image-to-video8image-to-3d8image-text-to-image03 smaller tags4all generation4,685Oct 2024text-to-image4,055image-to-image150unconditional-image-generation57text-to-video14image-to-video4image-to-3d13image-text-to-image03 smaller tags9all generation4,302Nov 2024text-to-image4,415image-to-image30unconditional-image-generation90text-to-video10image-to-video11image-to-3d11image-text-to-image03 smaller tags3all generation4,570Dec 2024text-to-image4,369image-to-image51unconditional-image-generation70text-to-video36image-to-video12image-to-3d19image-text-to-image03 smaller tags7all generation4,564Jan 2025text-to-image5,271image-to-image21unconditional-image-generation54text-to-video72image-to-video6image-to-3d17image-text-to-image03 smaller tags4all generation5,445Feb 2025text-to-image5,554image-to-image67unconditional-image-generation63text-to-video52image-to-video19image-to-3d11image-text-to-image03 smaller tags11all generation5,777Mar 2025text-to-image6,071image-to-image141unconditional-image-generation66text-to-video119image-to-video58image-to-3d29image-text-to-image03 smaller tags8all generation6,492Apr 2025text-to-image4,364image-to-image115unconditional-image-generation83text-to-video39image-to-video40image-to-3d12image-text-to-image03 smaller tags6all generation4,659May 2025text-to-image3,838image-to-image47unconditional-image-generation27text-to-video37image-to-video31image-to-3d27image-text-to-image03 smaller tags19all generation4,026Jun 2025text-to-image3,783image-to-image78unconditional-image-generation44text-to-video29image-to-video26image-to-3d22image-text-to-image03 smaller tags12all generation3,994Jul 2025text-to-image2,822image-to-image159unconditional-image-generation48text-to-video50image-to-video30image-to-3d16image-text-to-image03 smaller tags11all generation3,136Aug 2025text-to-image4,652image-to-image80unconditional-image-generation49text-to-video40image-to-video31image-to-3d15image-text-to-image03 smaller tags10all generation4,877Sep 2025text-to-image2,488image-to-image147unconditional-image-generation59text-to-video43image-to-video55image-to-3d18image-text-to-image03 smaller tags8all generation2,818Oct 2025text-to-image1,898image-to-image104unconditional-image-generation62text-to-video127image-to-video67image-to-3d17image-text-to-image13 smaller tags14all generation2,290Nov 2025text-to-image990image-to-image83unconditional-image-generation52text-to-video37image-to-video46image-to-3d13image-text-to-image13 smaller tags8all generation1,230Dec 2025text-to-image1,035image-to-image76unconditional-image-generation58text-to-video41image-to-video33image-to-3d31image-text-to-image203 smaller tags12all generation1,306Jan 2026text-to-image1,098image-to-image152unconditional-image-generation56text-to-video55image-to-video59image-to-3d15image-text-to-image143 smaller tags15all generation1,464Feb 2026text-to-image1,297image-to-image139unconditional-image-generation45text-to-video34image-to-video54image-to-3d27image-text-to-image83 smaller tags32all generation1,636Mar 2026text-to-image1,575image-to-image200unconditional-image-generation45text-to-video98image-to-video174image-to-3d40image-text-to-image113 smaller tags61all generation2,204Apr 2026text-to-image1,270image-to-image172unconditional-image-generation50text-to-video104image-to-video142image-to-3d40image-text-to-image183 smaller tags55all generation1,851May 2026text-to-image3,304image-to-image180unconditional-image-generation48text-to-video596image-to-video144image-to-3d56image-text-to-image393 smaller tags44all generation4,411Jun 2026text-to-image6,205image-to-image274unconditional-image-generation44text-to-video362image-to-video108image-to-3d45image-text-to-image133 smaller tags49all generation7,100Jul 2026text-to-image1,271image-to-image289unconditional-image-generation51text-to-video145image-to-video160image-to-3d57image-text-to-image103 smaller tags41all generation2,024Aug 2026text-to-image1,252image-to-image305unconditional-image-generation40text-to-video264image-to-video184image-to-3d45image-text-to-image63 smaller tags206all generation2,302Sep 2026text-to-image1,668image-to-image274unconditional-image-generation53text-to-video222image-to-video132image-to-3d63image-text-to-image4113 smaller tags121all generation2,944Oct 2026text-to-image32image-to-image4unconditional-image-generation0text-to-video2image-to-video1image-to-3d0image-text-to-image73 smaller tags1all generation47
image-text-to-text 41Kany-to-any 12Kimage-to-text 2.2Kvisual-question-answering 857video-text-to-text 498document-question-answering 246
02,0004,0006,0002023202420252026Apr 2022image-text-to-text5any-to-any0image-to-text7visual-question-answering0video-text-to-text0document-question-answering0all vision-language12May 2022image-text-to-text1any-to-any0image-to-text0visual-question-answering0video-text-to-text0document-question-answering1all vision-language2Jun 2022image-text-to-text5any-to-any0image-to-text0visual-question-answering0video-text-to-text0document-question-answering0all vision-language5Jul 2022image-text-to-text18any-to-any0image-to-text7visual-question-answering0video-text-to-text0document-question-answering2all vision-language27Aug 2022image-text-to-text17any-to-any0image-to-text13visual-question-answering0video-text-to-text0document-question-answering1all vision-language31Sep 2022image-text-to-text44any-to-any0image-to-text3visual-question-answering0video-text-to-text0document-question-answering1all vision-language48Oct 2022image-text-to-text27any-to-any0image-to-text3visual-question-answering0video-text-to-text0document-question-answering1all vision-language31Nov 2022image-text-to-text73any-to-any0image-to-text6visual-question-answering1video-text-to-text0document-question-answering1all vision-language81Dec 2022image-text-to-text27any-to-any0image-to-text10visual-question-answering5video-text-to-text0document-question-answering1all vision-language43Jan 2023image-text-to-text33any-to-any0image-to-text21visual-question-answering3video-text-to-text0document-question-answering0all vision-language57Feb 2023image-text-to-text56any-to-any0image-to-text9visual-question-answering2video-text-to-text0document-question-answering2all vision-language69Mar 2023image-text-to-text50any-to-any0image-to-text14visual-question-answering16video-text-to-text0document-question-answering3all vision-language83Apr 2023image-text-to-text96any-to-any0image-to-text10visual-question-answering13video-text-to-text1document-question-answering7all vision-language127May 2023image-text-to-text149any-to-any0image-to-text29visual-question-answering5video-text-to-text0document-question-answering8all vision-language191Jun 2023image-text-to-text127any-to-any0image-to-text25visual-question-answering4video-text-to-text0document-question-answering6all vision-language162Jul 2023image-text-to-text125any-to-any0image-to-text35visual-question-answering11video-text-to-text0document-question-answering3all vision-language174Aug 2023image-text-to-text185any-to-any0image-to-text17visual-question-answering4video-text-to-text0document-question-answering7all vision-language213Sep 2023image-text-to-text135any-to-any0image-to-text39visual-question-answering8video-text-to-text1document-question-answering8all vision-language191Oct 2023image-text-to-text191any-to-any0image-to-text28visual-question-answering8video-text-to-text0document-question-answering14all vision-language241Nov 2023image-text-to-text194any-to-any0image-to-text15visual-question-answering15video-text-to-text1document-question-answering36all vision-language261Dec 2023image-text-to-text237any-to-any0image-to-text25visual-question-answering15video-text-to-text0document-question-answering20all vision-language297Jan 2024image-text-to-text213any-to-any0image-to-text29visual-question-answering15video-text-to-text0document-question-answering11all vision-language268Feb 2024image-text-to-text210any-to-any0image-to-text33visual-question-answering27video-text-to-text0document-question-answering7all vision-language277Mar 2024image-text-to-text319any-to-any12image-to-text28visual-question-answering17video-text-to-text0document-question-answering11all vision-language387Apr 2024image-text-to-text378any-to-any0image-to-text45visual-question-answering44video-text-to-text5document-question-answering11all vision-language483May 2024image-text-to-text479any-to-any3image-to-text40visual-question-answering40video-text-to-text0document-question-answering7all vision-language569Jun 2024image-text-to-text365any-to-any20image-to-text57visual-question-answering37video-text-to-text7document-question-answering4all vision-language490Jul 2024image-text-to-text357any-to-any36image-to-text40visual-question-answering23video-text-to-text3document-question-answering4all vision-language463Aug 2024image-text-to-text338any-to-any172image-to-text23visual-question-answering22video-text-to-text5document-question-answering4all vision-language564Sep 2024image-text-to-text289any-to-any530image-to-text34visual-question-answering16video-text-to-text9document-question-answering1all vision-language879Oct 2024image-text-to-text345any-to-any594image-to-text30visual-question-answering18video-text-to-text6document-question-answering6all vision-language999Nov 2024image-text-to-text388any-to-any1,260image-to-text23visual-question-answering20video-text-to-text6document-question-answering8all vision-language1,705Dec 2024image-text-to-text525any-to-any669image-to-text14visual-question-answering15video-text-to-text18document-question-answering2all vision-language1,243Jan 2025image-text-to-text478any-to-any815image-to-text23visual-question-answering15video-text-to-text15document-question-answering8all vision-language1,354Feb 2025image-text-to-text616any-to-any285image-to-text12visual-question-answering13video-text-to-text11document-question-answering3all vision-language940Mar 2025image-text-to-text983any-to-any385image-to-text18visual-question-answering17video-text-to-text24document-question-answering2all vision-language1,429Apr 2025image-text-to-text930any-to-any239image-to-text21visual-question-answering31video-text-to-text23document-question-answering6all vision-language1,250May 2025image-text-to-text874any-to-any198image-to-text25visual-question-answering26video-text-to-text20document-question-answering0all vision-language1,143Jun 2025image-text-to-text865any-to-any149image-to-text99visual-question-answering15video-text-to-text15document-question-answering4all vision-language1,147Jul 2025image-text-to-text1,005any-to-any417image-to-text47visual-question-answering22video-text-to-text8document-question-answering1all vision-language1,500Aug 2025image-text-to-text921any-to-any198image-to-text38visual-question-answering10video-text-to-text5document-question-answering2all vision-language1,174Sep 2025image-text-to-text927any-to-any307image-to-text38visual-question-answering13video-text-to-text10document-question-answering1all vision-language1,296Oct 2025image-text-to-text1,129any-to-any344image-to-text59visual-question-answering10video-text-to-text12document-question-answering4all vision-language1,558Nov 2025image-text-to-text1,049any-to-any685image-to-text37visual-question-answering8video-text-to-text20document-question-answering0all vision-language1,799Dec 2025image-text-to-text1,168any-to-any355image-to-text51visual-question-answering3video-text-to-text31document-question-answering0all vision-language1,608Jan 2026image-text-to-text1,089any-to-any2,401image-to-text57visual-question-answering9video-text-to-text14document-question-answering1all vision-language3,571Feb 2026image-text-to-text1,141any-to-any36image-to-text87visual-question-answering15video-text-to-text19document-question-answering2all vision-language1,300Mar 2026image-text-to-text2,100any-to-any59image-to-text106visual-question-answering18video-text-to-text17document-question-answering5all vision-language2,305Apr 2026image-text-to-text3,601any-to-any473image-to-text128visual-question-answering15video-text-to-text15document-question-answering0all vision-language4,232May 2026image-text-to-text2,670any-to-any215image-to-text113visual-question-answering23video-text-to-text31document-question-answering1all vision-language3,053Jun 2026image-text-to-text2,461any-to-any419image-to-text134visual-question-answering23video-text-to-text27document-question-answering0all vision-language3,064Jul 2026image-text-to-text2,896any-to-any147image-to-text110visual-question-answering27video-text-to-text62document-question-answering0all vision-language3,242Aug 2026image-text-to-text4,286any-to-any154image-to-text118visual-question-answering58video-text-to-text35document-question-answering1all vision-language4,652Sep 2026image-text-to-text3,577any-to-any130image-to-text108visual-question-answering77video-text-to-text21document-question-answering1all vision-language3,914Oct 2026image-text-to-text48any-to-any6image-to-text1visual-question-answering3video-text-to-text1document-question-answering0all vision-language59
image-classification 29K
01,0002,0003,0002023202420252026Apr 2022image-classification71all classification71May 2022image-classification62all classification62Jun 2022image-classification100all classification100Jul 2022image-classification129all classification129Aug 2022image-classification70all classification70Sep 2022image-classification105all classification105Oct 2022image-classification115all classification115Nov 2022image-classification143all classification143Dec 2022image-classification395all classification395Jan 2023image-classification275all classification275Feb 2023image-classification276all classification276Mar 2023image-classification524all classification524Apr 2023image-classification707all classification707May 2023image-classification412all classification412Jun 2023image-classification391all classification391Jul 2023image-classification481all classification481Aug 2023image-classification491all classification491Sep 2023image-classification475all classification475Oct 2023image-classification499all classification499Nov 2023image-classification1,010all classification1,010Dec 2023image-classification1,301all classification1,301Jan 2024image-classification481all classification481Feb 2024image-classification586all classification586Mar 2024image-classification584all classification584Apr 2024image-classification662all classification662May 2024image-classification1,099all classification1,099Jun 2024image-classification828all classification828Jul 2024image-classification466all classification466Aug 2024image-classification186all classification186Sep 2024image-classification347all classification347Oct 2024image-classification607all classification607Nov 2024image-classification439all classification439Dec 2024image-classification2,340all classification2,340Jan 2025image-classification415all classification415Feb 2025image-classification422all classification422Mar 2025image-classification1,917all classification1,917Apr 2025image-classification963all classification963May 2025image-classification665all classification665Jun 2025image-classification610all classification610Jul 2025image-classification305all classification305Aug 2025image-classification324all classification324Sep 2025image-classification357all classification357Oct 2025image-classification846all classification846Nov 2025image-classification302all classification302Dec 2025image-classification370all classification370Jan 2026image-classification285all classification285Feb 2026image-classification685all classification685Mar 2026image-classification441all classification441Apr 2026image-classification558all classification558May 2026image-classification523all classification523Jun 2026image-classification416all classification416Jul 2026image-classification623all classification623Aug 2026image-classification637all classification637Sep 2026image-classification707all classification707Oct 2026image-classification3all classification3
object-detection 6.8Kzero-shot-object-detection 139
02004006002023202420252026Apr 2022object-detection6zero-shot-object-detection0all detection6May 2022object-detection4zero-shot-object-detection0all detection4Jun 2022object-detection5zero-shot-object-detection0all detection5Jul 2022object-detection11zero-shot-object-detection3all detection14Aug 2022object-detection3zero-shot-object-detection0all detection3Sep 2022object-detection6zero-shot-object-detection0all detection6Oct 2022object-detection11zero-shot-object-detection0all detection11Nov 2022object-detection4zero-shot-object-detection0all detection4Dec 2022object-detection41zero-shot-object-detection0all detection41Jan 2023object-detection81zero-shot-object-detection0all detection81Feb 2023object-detection34zero-shot-object-detection0all detection34Mar 2023object-detection84zero-shot-object-detection1all detection85Apr 2023object-detection53zero-shot-object-detection0all detection53May 2023object-detection46zero-shot-object-detection0all detection46Jun 2023object-detection63zero-shot-object-detection0all detection63Jul 2023object-detection78zero-shot-object-detection1all detection79Aug 2023object-detection100zero-shot-object-detection0all detection100Sep 2023object-detection124zero-shot-object-detection2all detection126Oct 2023object-detection289zero-shot-object-detection6all detection295Nov 2023object-detection130zero-shot-object-detection3all detection133Dec 2023object-detection79zero-shot-object-detection0all detection79Jan 2024object-detection86zero-shot-object-detection1all detection87Feb 2024object-detection96zero-shot-object-detection9all detection105Mar 2024object-detection85zero-shot-object-detection1all detection86Apr 2024object-detection199zero-shot-object-detection4all detection203May 2024object-detection195zero-shot-object-detection0all detection195Jun 2024object-detection189zero-shot-object-detection4all detection193Jul 2024object-detection136zero-shot-object-detection0all detection136Aug 2024object-detection179zero-shot-object-detection0all detection179Sep 2024object-detection76zero-shot-object-detection1all detection77Oct 2024object-detection132zero-shot-object-detection0all detection132Nov 2024object-detection110zero-shot-object-detection1all detection111Dec 2024object-detection88zero-shot-object-detection0all detection88Jan 2025object-detection102zero-shot-object-detection5all detection107Feb 2025object-detection93zero-shot-object-detection2all detection95Mar 2025object-detection119zero-shot-object-detection8all detection127Apr 2025object-detection156zero-shot-object-detection6all detection162May 2025object-detection99zero-shot-object-detection11all detection110Jun 2025object-detection111zero-shot-object-detection5all detection116Jul 2025object-detection75zero-shot-object-detection4all detection79Aug 2025object-detection58zero-shot-object-detection4all detection62Sep 2025object-detection99zero-shot-object-detection0all detection99Oct 2025object-detection227zero-shot-object-detection3all detection230Nov 2025object-detection78zero-shot-object-detection4all detection82Dec 2025object-detection115zero-shot-object-detection4all detection119Jan 2026object-detection135zero-shot-object-detection6all detection141Feb 2026object-detection194zero-shot-object-detection1all detection195Mar 2026object-detection240zero-shot-object-detection3all detection243Apr 2026object-detection282zero-shot-object-detection3all detection285May 2026object-detection298zero-shot-object-detection5all detection303Jun 2026object-detection329zero-shot-object-detection2all detection331Jul 2026object-detection303zero-shot-object-detection19all detection322Aug 2026object-detection476zero-shot-object-detection6all detection482Sep 2026object-detection417zero-shot-object-detection1all detection418Oct 2026object-detection2zero-shot-object-detection0all detection2
zero-shot-image-classification 2.2Kimage-feature-extraction 1.6Kvisual-document-retrieval 183
02004006002023202420252026Apr 2022zero-shot-image-classification3image-feature-extraction3visual-document-retrieval0all embeddings6May 2022zero-shot-image-classification0image-feature-extraction1visual-document-retrieval0all embeddings1Jun 2022zero-shot-image-classification0image-feature-extraction0visual-document-retrieval0all embeddings0Jul 2022zero-shot-image-classification4image-feature-extraction0visual-document-retrieval0all embeddings4Aug 2022zero-shot-image-classification10image-feature-extraction1visual-document-retrieval0all embeddings11Sep 2022zero-shot-image-classification7image-feature-extraction5visual-document-retrieval0all embeddings12Oct 2022zero-shot-image-classification2image-feature-extraction2visual-document-retrieval0all embeddings4Nov 2022zero-shot-image-classification7image-feature-extraction3visual-document-retrieval0all embeddings10Dec 2022zero-shot-image-classification4image-feature-extraction9visual-document-retrieval0all embeddings13Jan 2023zero-shot-image-classification10image-feature-extraction8visual-document-retrieval0all embeddings18Feb 2023zero-shot-image-classification10image-feature-extraction1visual-document-retrieval0all embeddings11Mar 2023zero-shot-image-classification10image-feature-extraction51visual-document-retrieval0all embeddings61Apr 2023zero-shot-image-classification38image-feature-extraction0visual-document-retrieval0all embeddings38May 2023zero-shot-image-classification16image-feature-extraction22visual-document-retrieval0all embeddings38Jun 2023zero-shot-image-classification15image-feature-extraction8visual-document-retrieval0all embeddings23Jul 2023zero-shot-image-classification5image-feature-extraction8visual-document-retrieval0all embeddings13Aug 2023zero-shot-image-classification13image-feature-extraction2visual-document-retrieval0all embeddings15Sep 2023zero-shot-image-classification13image-feature-extraction9visual-document-retrieval0all embeddings22Oct 2023zero-shot-image-classification39image-feature-extraction6visual-document-retrieval0all embeddings45Nov 2023zero-shot-image-classification15image-feature-extraction5visual-document-retrieval0all embeddings20Dec 2023zero-shot-image-classification25image-feature-extraction9visual-document-retrieval0all embeddings34Jan 2024zero-shot-image-classification46image-feature-extraction4visual-document-retrieval0all embeddings50Feb 2024zero-shot-image-classification25image-feature-extraction7visual-document-retrieval0all embeddings32Mar 2024zero-shot-image-classification49image-feature-extraction13visual-document-retrieval0all embeddings62Apr 2024zero-shot-image-classification16image-feature-extraction24visual-document-retrieval0all embeddings40May 2024zero-shot-image-classification24image-feature-extraction35visual-document-retrieval0all embeddings59Jun 2024zero-shot-image-classification61image-feature-extraction17visual-document-retrieval1all embeddings79Jul 2024zero-shot-image-classification33image-feature-extraction34visual-document-retrieval0all embeddings67Aug 2024zero-shot-image-classification56image-feature-extraction33visual-document-retrieval3all embeddings92Sep 2024zero-shot-image-classification11image-feature-extraction26visual-document-retrieval3all embeddings40Oct 2024zero-shot-image-classification40image-feature-extraction21visual-document-retrieval3all embeddings64Nov 2024zero-shot-image-classification32image-feature-extraction20visual-document-retrieval8all embeddings60Dec 2024zero-shot-image-classification32image-feature-extraction128visual-document-retrieval5all embeddings165Jan 2025zero-shot-image-classification18image-feature-extraction17visual-document-retrieval8all embeddings43Feb 2025zero-shot-image-classification99image-feature-extraction42visual-document-retrieval7all embeddings148Mar 2025zero-shot-image-classification16image-feature-extraction16visual-document-retrieval13all embeddings45Apr 2025zero-shot-image-classification17image-feature-extraction38visual-document-retrieval4all embeddings59May 2025zero-shot-image-classification17image-feature-extraction72visual-document-retrieval3all embeddings92Jun 2025zero-shot-image-classification32image-feature-extraction29visual-document-retrieval9all embeddings70Jul 2025zero-shot-image-classification30image-feature-extraction38visual-document-retrieval6all embeddings74Aug 2025zero-shot-image-classification17image-feature-extraction45visual-document-retrieval10all embeddings72Sep 2025zero-shot-image-classification40image-feature-extraction39visual-document-retrieval13all embeddings92Oct 2025zero-shot-image-classification26image-feature-extraction22visual-document-retrieval3all embeddings51Nov 2025zero-shot-image-classification57image-feature-extraction23visual-document-retrieval6all embeddings86Dec 2025zero-shot-image-classification17image-feature-extraction43visual-document-retrieval10all embeddings70Jan 2026zero-shot-image-classification32image-feature-extraction29visual-document-retrieval12all embeddings73Feb 2026zero-shot-image-classification33image-feature-extraction40visual-document-retrieval3all embeddings76Mar 2026zero-shot-image-classification277image-feature-extraction56visual-document-retrieval4all embeddings337Apr 2026zero-shot-image-classification67image-feature-extraction73visual-document-retrieval11all embeddings151May 2026zero-shot-image-classification102image-feature-extraction54visual-document-retrieval3all embeddings159Jun 2026zero-shot-image-classification412image-feature-extraction92visual-document-retrieval4all embeddings508Jul 2026zero-shot-image-classification67image-feature-extraction111visual-document-retrieval14all embeddings192Aug 2026zero-shot-image-classification61image-feature-extraction83visual-document-retrieval12all embeddings156Sep 2026zero-shot-image-classification45image-feature-extraction107visual-document-retrieval5all embeddings157Oct 2026zero-shot-image-classification2image-feature-extraction1visual-document-retrieval0all embeddings3
image-segmentation 3.5Kmask-generation 305
01002003004002023202420252026Apr 2022image-segmentation10mask-generation0all segmentation10May 2022image-segmentation13mask-generation0all segmentation13Jun 2022image-segmentation5mask-generation0all segmentation5Jul 2022image-segmentation4mask-generation0all segmentation4Aug 2022image-segmentation4mask-generation0all segmentation4Sep 2022image-segmentation5mask-generation0all segmentation5Oct 2022image-segmentation2mask-generation0all segmentation2Nov 2022image-segmentation17mask-generation0all segmentation17Dec 2022image-segmentation6mask-generation0all segmentation6Jan 2023image-segmentation59mask-generation0all segmentation59Feb 2023image-segmentation8mask-generation0all segmentation8Mar 2023image-segmentation16mask-generation0all segmentation16Apr 2023image-segmentation17mask-generation5all segmentation22May 2023image-segmentation13mask-generation7all segmentation20Jun 2023image-segmentation13mask-generation0all segmentation13Jul 2023image-segmentation15mask-generation9all segmentation24Aug 2023image-segmentation13mask-generation0all segmentation13Sep 2023image-segmentation22mask-generation2all segmentation24Oct 2023image-segmentation26mask-generation0all segmentation26Nov 2023image-segmentation26mask-generation3all segmentation29Dec 2023image-segmentation51mask-generation4all segmentation55Jan 2024image-segmentation31mask-generation10all segmentation41Feb 2024image-segmentation109mask-generation4all segmentation113Mar 2024image-segmentation82mask-generation5all segmentation87Apr 2024image-segmentation29mask-generation2all segmentation31May 2024image-segmentation48mask-generation5all segmentation53Jun 2024image-segmentation39mask-generation8all segmentation47Jul 2024image-segmentation68mask-generation8all segmentation76Aug 2024image-segmentation65mask-generation12all segmentation77Sep 2024image-segmentation82mask-generation19all segmentation101Oct 2024image-segmentation46mask-generation5all segmentation51Nov 2024image-segmentation46mask-generation3all segmentation49Dec 2024image-segmentation61mask-generation3all segmentation64Jan 2025image-segmentation44mask-generation5all segmentation49Feb 2025image-segmentation32mask-generation4all segmentation36Mar 2025image-segmentation111mask-generation13all segmentation124Apr 2025image-segmentation64mask-generation9all segmentation73May 2025image-segmentation123mask-generation4all segmentation127Jun 2025image-segmentation285mask-generation3all segmentation288Jul 2025image-segmentation66mask-generation3all segmentation69Aug 2025image-segmentation49mask-generation3all segmentation52Sep 2025image-segmentation61mask-generation3all segmentation64Oct 2025image-segmentation73mask-generation2all segmentation75Nov 2025image-segmentation51mask-generation11all segmentation62Dec 2025image-segmentation70mask-generation5all segmentation75Jan 2026image-segmentation60mask-generation2all segmentation62Feb 2026image-segmentation93mask-generation6all segmentation99Mar 2026image-segmentation142mask-generation10all segmentation152Apr 2026image-segmentation99mask-generation11all segmentation110May 2026image-segmentation171mask-generation12all segmentation183Jun 2026image-segmentation144mask-generation9all segmentation153Jul 2026image-segmentation283mask-generation48all segmentation331Aug 2026image-segmentation201mask-generation18all segmentation219Sep 2026image-segmentation218mask-generation10all segmentation228Oct 2026image-segmentation4mask-generation0all segmentation4
video-classification 2.2K
0501001502002023202420252026Apr 2022video-classification0all video classification0May 2022video-classification0all video classification0Jun 2022video-classification0all video classification0Jul 2022video-classification2all video classification2Aug 2022video-classification9all video classification9Sep 2022video-classification17all video classification17Oct 2022video-classification6all video classification6Nov 2022video-classification7all video classification7Dec 2022video-classification11all video classification11Jan 2023video-classification17all video classification17Feb 2023video-classification12all video classification12Mar 2023video-classification17all video classification17Apr 2023video-classification17all video classification17May 2023video-classification41all video classification41Jun 2023video-classification32all video classification32Jul 2023video-classification36all video classification36Aug 2023video-classification26all video classification26Sep 2023video-classification57all video classification57Oct 2023video-classification48all video classification48Nov 2023video-classification51all video classification51Dec 2023video-classification69all video classification69Jan 2024video-classification41all video classification41Feb 2024video-classification87all video classification87Mar 2024video-classification106all video classification106Apr 2024video-classification85all video classification85May 2024video-classification128all video classification128Jun 2024video-classification64all video classification64Jul 2024video-classification106all video classification106Aug 2024video-classification20all video classification20Sep 2024video-classification19all video classification19Oct 2024video-classification23all video classification23Nov 2024video-classification60all video classification60Dec 2024video-classification56all video classification56Jan 2025video-classification66all video classification66Feb 2025video-classification68all video classification68Mar 2025video-classification43all video classification43Apr 2025video-classification47all video classification47May 2025video-classification94all video classification94Jun 2025video-classification58all video classification58Jul 2025video-classification21all video classification21Aug 2025video-classification52all video classification52Sep 2025video-classification45all video classification45Oct 2025video-classification17all video classification17Nov 2025video-classification171all video classification171Dec 2025video-classification34all video classification34Jan 2026video-classification18all video classification18Feb 2026video-classification8all video classification8Mar 2026video-classification27all video classification27Apr 2026video-classification20all video classification20May 2026video-classification29all video classification29Jun 2026video-classification33all video classification33Jul 2026video-classification37all video classification37Aug 2026video-classification38all video classification38Sep 2026video-classification29all video classification29Oct 2026video-classification0all video classification0
depth-estimation 597keypoint-detection 426
03060901202023202420252026Apr 2022depth-estimation0keypoint-detection0all depth & pose0May 2022depth-estimation0keypoint-detection1all depth & pose1Jun 2022depth-estimation0keypoint-detection0all depth & pose0Jul 2022depth-estimation0keypoint-detection0all depth & pose0Aug 2022depth-estimation0keypoint-detection0all depth & pose0Sep 2022depth-estimation0keypoint-detection0all depth & pose0Oct 2022depth-estimation0keypoint-detection0all depth & pose0Nov 2022depth-estimation0keypoint-detection6all depth & pose6Dec 2022depth-estimation1keypoint-detection0all depth & pose1Jan 2023depth-estimation1keypoint-detection0all depth & pose1Feb 2023depth-estimation1keypoint-detection0all depth & pose1Mar 2023depth-estimation2keypoint-detection0all depth & pose2Apr 2023depth-estimation3keypoint-detection0all depth & pose3May 2023depth-estimation7keypoint-detection1all depth & pose8Jun 2023depth-estimation11keypoint-detection0all depth & pose11Jul 2023depth-estimation0keypoint-detection1all depth & pose1Aug 2023depth-estimation1keypoint-detection1all depth & pose2Sep 2023depth-estimation2keypoint-detection1all depth & pose3Oct 2023depth-estimation5keypoint-detection0all depth & pose5Nov 2023depth-estimation10keypoint-detection0all depth & pose10Dec 2023depth-estimation4keypoint-detection0all depth & pose4Jan 2024depth-estimation13keypoint-detection0all depth & pose13Feb 2024depth-estimation2keypoint-detection3all depth & pose5Mar 2024depth-estimation2keypoint-detection2all depth & pose4Apr 2024depth-estimation10keypoint-detection2all depth & pose12May 2024depth-estimation4keypoint-detection1all depth & pose5Jun 2024depth-estimation17keypoint-detection0all depth & pose17Jul 2024depth-estimation12keypoint-detection1all depth & pose13Aug 2024depth-estimation7keypoint-detection0all depth & pose7Sep 2024depth-estimation20keypoint-detection10all depth & pose30Oct 2024depth-estimation14keypoint-detection4all depth & pose18Nov 2024depth-estimation7keypoint-detection4all depth & pose11Dec 2024depth-estimation12keypoint-detection3all depth & pose15Jan 2025depth-estimation8keypoint-detection10all depth & pose18Feb 2025depth-estimation6keypoint-detection2all depth & pose8Mar 2025depth-estimation10keypoint-detection0all depth & pose10Apr 2025depth-estimation5keypoint-detection2all depth & pose7May 2025depth-estimation3keypoint-detection1all depth & pose4Jun 2025depth-estimation6keypoint-detection4all depth & pose10Jul 2025depth-estimation0keypoint-detection2all depth & pose2Aug 2025depth-estimation13keypoint-detection4all depth & pose17Sep 2025depth-estimation8keypoint-detection3all depth & pose11Oct 2025depth-estimation8keypoint-detection2all depth & pose10Nov 2025depth-estimation13keypoint-detection3all depth & pose16Dec 2025depth-estimation13keypoint-detection18all depth & pose31Jan 2026depth-estimation9keypoint-detection61all depth & pose70Feb 2026depth-estimation8keypoint-detection84all depth & pose92Mar 2026depth-estimation42keypoint-detection18all depth & pose60Apr 2026depth-estimation41keypoint-detection17all depth & pose58May 2026depth-estimation35keypoint-detection15all depth & pose50Jun 2026depth-estimation30keypoint-detection42all depth & pose72Jul 2026depth-estimation43keypoint-detection23all depth & pose66Aug 2026depth-estimation58keypoint-detection36all depth & pose94Sep 2026depth-estimation65keypoint-detection37all depth & pose102Oct 2026depth-estimation0keypoint-detection1all depth & pose1

The current month is partial — 1 of 31 days.

Each field on its own scale

A shared axis would flatten most of these into nothing: Generation is 121× Depth & pose. Each sparkline is scaled to its own field, so what you compare is shape, not size. Growth is the last 12 months against the 12 before.

Generation

Vision-language

Classification

Detection

Embeddings

Segmentation

Video classification

Depth & pose

Where transformers is the library

The library each repo declares, as a share of the repos created in the last 12 months and of the last 30 days of downloads. transformers is the dark segment; the two biggest other libraries follow, then the rest. Repo counts show who ships, downloads show what gets used.

repos, last 12 monthsdownloads, last 30 daystf repostf dl
Generation
diffusers 78%
diffusers 56%300 others 31%
1%0%
Vision-language
transformers 58%no library 23%
transformers 82%
58%82%
Classification
transformers 26%no library 31%111 others 35%
transformers 32%timm 65%
26%32%
Detection
transformers 19%ultralytics 28%no library 24%115 others 30%
transformers 57%gguf 38%
19%57%
Embeddings
transformers 29%sentence-transformers 27%78 others 35%
transformers 75%open_clip 15%
29%75%
Segmentation
transformers 16%no library 24%pytorch 14%117 others 46%
transformers 81%
16%81%
Video classification
transformers 36%no library 41%
transformers 97%
36%97%
Depth & pose
no library 21%pytorch 15%58 others 59%
transformers 78%depth-anything-3 17%
5%78%
text-to-image
diffusers 88%
diffusers 84%
0%0%
image-to-image
diffusers 49%no library 17%107 others 32%
diffusers 70%107 others 19%
2%1%
unconditional-image-generation
diffusers 83%
diffusers 97%
0%1%
text-to-video
diffusers 62%no library 16%60 others 20%
diffusers 53%gguf 22%60 others 25%
1%0%
image-to-video
diffusers 54%no library 20%53 others 26%
diffusion-single-file 48%diffusers 34%53 others 19%
0%0%
image-to-3d
no library 32%diffusers 14%63 others 53%
trellis 41%trellis2 30%63 others 29%
1%0%
image-text-to-image
no library 81%
diffusers 52%ggml 24%
7%10%
video-to-video
no library 32%diffusers 31%30 others 36%
diffusers 70%30 others 19%
1%0%
image-text-to-video
no library 28%diffusers 27%15 others 45%
minimax-h3 57%gguf 21%15 others 22%
0%0%
text-to-3d
no library 45%trellis 16%12 others 29%
trellis 51%diffusers 21%12 others 17%
10%11%
image-text-to-text
transformers 66%
transformers 81%
66%81%
any-to-any
transformers 22%no library 71%
transformers 92%
22%92%
image-to-text
transformers 29%no library 32%74 others 32%
transformers 67%PaddleOCR 26%
29%67%
visual-question-answering
transformers 23%no library 60%
transformers 94%
23%94%
video-text-to-text
transformers 70%no library 22%
transformers 97%
70%97%
document-question-answering
transformers 20%no library 40%8 others 33%
transformers 100%
20%100%
image-classification
transformers 26%no library 31%111 others 35%
transformers 32%timm 65%
26%32%
object-detection
transformers 19%ultralytics 28%no library 23%113 others 29%
transformers 44%gguf 51%
19%44%
zero-shot-object-detection
no library 35%zeromodels 19%10 others 33%
transformers 98%
12%98%
zero-shot-image-classification
transformers 29%sentence-transformers 45%25 others 15%
transformers 79%open_clip 20%
29%79%
image-feature-extraction
transformers 29%timm 17%no library 16%61 others 38%
transformers 67%timm 30%
29%67%
visual-document-retrieval
transformers 32%15 others 47%
transformers 25%colpali 56%colpali_engine 16%
32%25%
image-segmentation
no library 25%pytorch 15%110 others 46%
transformers 74%birefnet 18%
13%74%
mask-generation
transformers 41%18 others 42%
transformers 96%
41%96%
video-classification
transformers 36%no library 41%
transformers 97%
36%97%
depth-estimation
no library 25%pytorch 15%40 others 53%
transformers 74%depth-anything-3 21%
8%74%
keypoint-detection
vismatch 21%image-matching-models 19%35 others 59%
transformers 96%
2%96%

Who ships what the field actually uses

A contribution grid weighted by engagement, not output: labs ranked by the likes their vision models have earned, months across, darker where a month's releases landed. Counting repos instead would rank format converters and checkpoint farms above every research lab — Qwen earns 65K likes from 44 models while timm earns 1.6K from 1,785. Sibling repos are collapsed into one model, so a family of sizes or fine-tunes counts once rather than once per repo. The dot is the field each lab mostly works in; hover a row for its most-liked model.

The landmarks, all on one timeline

The most-liked release from each field, ringed in its colour. Hover for the model, click to open it on the Hub.

Generationstable-diffusion-v1-4CompVis/stable-diffusion-v1-42022-08-20684K · 7,104 likesVideo classificationxclip-base-patch32microsoft/xclip-base-patch322022-08-25106K · 119 likesDetectiontable-transformer-detectiomicrosoft/table-transformer-detection2022-10-14537K · 430 likesGenerationOrangeMixsWarriorMama777/OrangeMixs2022-12-041.4K · 3,958 likesGenerationstable-diffusion-xl-base-1stabilityai/stable-diffusion-xl-base-1.02023-07-254.1M · 8,257 likesDetectionstockmarket-pattern-detectfoduucom/stockmarket-pattern-detection-yolov82023-08-103.8K · 438 likesClassificationnsfw_image_detectionFalconsai/nsfw_image_detection2023-10-132.2M · 1,195 likesDepth & posemarigold-depth-v1-0prs-eth/marigold-depth-v1-02023-12-0511K · 143 likesSegmentationRMBG-1.4briaai/RMBG-1.42023-12-12294K · 2,033 likesEmbeddingssiglip-so400m-patch14-384google/siglip-so400m-patch14-3842024-01-081.3M · 691 likesVideo classificationface_emotion_recognitionElenaRyumina/face_emotion_recognition2024-01-190 · 132 likesDetectionYOLOv8Ultralytics/YOLOv82024-01-3115K · 387 likesGenerationstable-diffusion-3-mediumstabilityai/stable-diffusion-3-medium2024-05-302.8K · 5,055 likesDepth & poseDepth-Anything-V2-Largedepth-anything/Depth-Anything-V2-Large2024-06-13121K · 178 likesGenerationFLUX.1-devblack-forest-labs/FLUX.1-dev2024-07-31699K · 15,269 likesGenerationFLUX.1-schnellblack-forest-labs/FLUX.1-schnell2024-07-31588K · 6,076 likesDepth & poseDepthProapple/DepthPro2024-10-034.7K · 555 likesGenerationstable-diffusion-3.5-largestabilityai/stable-diffusion-3.5-large2024-10-22102K · 4,068 likesSegmentationRMBG-2.0briaai/RMBG-2.02024-10-29486K · 1,488 likesVideo classificationvjepa2-vitl-fpc64-256facebook/vjepa2-vitl-fpc64-2562025-05-31213K · 210 likesVideo classificationvideoprism-base-f16r288google/videoprism-base-f16r2882025-06-142.3K · 109 likesEmbeddingsdinov3-vitl16-pretrain-lvdfacebook/dinov3-vitl16-pretrain-lvd1689m2025-08-06638K · 982 likesClassificationpixai-tagger-v0.9pixai-labs/pixai-tagger-v0.92025-08-260 · 216 likesSegmentationsam3facebook/sam32025-11-072.2M · 3,654 likesGenerationZ-Image-TurboTongyi-MAI/Z-Image-Turbo2025-11-25589K · 5,395 likesVision-languagegemma-4-31B-itgoogle/gemma-4-31B-it2026-03-119.8M · 3,981 likesSegmentationsam3.1facebook/sam3.12026-03-2653K · 885 likesVision-languageQwen3.6-35B-A3B-UncensoredHauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive2026-04-17912K · 3,800 likesVision-languageKimi-K3moonshotai/Kimi-K32026-06-131.3M · 11,565 likesVision-languageUnlimited-OCRbaidu/Unlimited-OCR2026-06-191.5M · 4,316 likesGenerationLTX-2.5Lightricks/LTX-2.52026-07-231.6M · 5,761 likesGenerationMiniMax-H3MiniMaxAI/MiniMax-H32026-07-283.6M · 5,802 likesVision-languageQwen3.8Qwen/Qwen3.8-27B2026-08-057M · 16,682 likesVision-languageQwen3.8-Flash-NextQwen/Qwen3.8-Flash-Next2026-08-241.2M · 5,797 likesVision-languageDeepSeek-V4.1-Flashdeepseek-ai/DeepSeek-V4.1-Flash2026-09-10748K · 3,945 likesClassificationVisionHOPEPSRben/VisionHOPE2026-09-29305 · 351 likes
2023202420252026
Table view — every figure on this page
Every figure on this page, as text.
TaskModelsShareLast 12moPrior 12moGrowthtransformers dlLandmarks
Generation124,07254.5%30,76254,6600.56×0%353
Vision-language56,30224.7%34,29815,1802.26×82%252
Classification29,37112.9%6,3939,3640.68×32%52
Detection6,9893.1%3,1511,2882.45×57%64
Embeddings3,9541.7%2,0169842.05×75%116
Segmentation3,8371.7%1,7491,0461.67×81%72
Video classification2,2271.0%4616330.73×97%25
Depth & pose1,0230.4%7211315.50×78%59
text-to-image110,87048.7%22,86351,6820.44×0%52
image-to-image3,8701.7%2,2481,0862.07×1%52
unconditional-image-generation2,7651.2%6047100.85×1%21
text-to-video2,7651.2%2,0855413.85×0%52
image-to-video1,6660.7%1,3033234.03×0%52
image-to-3d7720.3%4492102.14×0%51
image-text-to-image5600.2%5520—10%17
video-to-video3460.2%290525.58×0%23
image-text-to-video3190.1%3190—0%21
text-to-3d1390.1%49560.88×11%12
image-text-to-text40,82717.9%27,1678,8573.07×81%52
any-to-any11,7135.1%5,4185,5160.98×92%52
image-to-text2,1610.9%1,1083882.86×67%52
visual-question-answering8570.4%2862151.33×94%52
video-text-to-text4980.2%3041611.89×97%33
document-question-answering2460.1%15430.35×100%11
image-classification29,37112.9%6,3939,3640.68×32%52
object-detection6,8503.0%3,0941,2422.49×44%52
zero-shot-object-detection1390.1%57461.24×98%12
zero-shot-image-classification2,1681.0%1,1963903.07×79%52
image-feature-extraction1,6030.7%7335051.45×67%52
visual-document-retrieval1830.1%87890.98×25%12
image-segmentation3,5321.6%1,6059881.62×74%52
mask-generation3050.1%144582.48×96%20
video-classification2,2271.0%4616330.73×97%25
depth-estimation5970.3%365923.97×74%39
keypoint-detection4260.2%356399.13×96%20