Visual AI Itọsọna
Awoṣe Itankale GLIDE
GLIDE jẹ arosọ OpenAI awoṣe itankale ọrọ-si-aworan ti o ṣe afihan awọn itọsi pẹlu 'itọnisọna-ọfẹ classifier' le lu awọn eto orisun-GAN tẹlẹ.
Gbọ si itọsọna yiiAI-ṣe afihan · ~2 min
Lori iwe yi2 min ka
Akopọ
O jẹ ọna ti o ṣe pataki lati lọ si DALL-E 2.
Jin Dive
Released by OpenAI in late 2021, GLIDE (Guided Language to Image Diffusion for Generation and Editing) demonstrated that diffusion models guided by text could produce photorealistic, prompt-faithful images. Its biggest contribution was comparing two ways to steer generation: CLIP guidance versus classifier-free guidance. The team found classifier-free guidance produced more realistic and better-aligned images, a result that shaped nearly every text-to-image model since. GLIDE also supported text-driven inpainting, letting users edit part of an image with a new prompt. It used a 3.5-billion-parameter diffusion model plus an upsampler. OpenAI released a smaller, filtered version publicly while withholding the full model over misuse concerns, and the DALL-E 2 research paper describes an unCLIP decoder that modifies the GLIDE architecture to accept CLIP-image conditioning.
Real-World imuse
Ṣiṣẹda aworan kan lati inu gbolohun ọrọ gẹgẹbi aaye ti a ṣalaye, ti n ṣe afihan iṣakojọpọ iṣotitọ ni kutukutu
Inkikun ti a ṣe idari ọrọ: boju-boju apakan ti fọto kan ati kikun pẹlu ohun tuntun ti a ṣalaye ninu awọn ọrọ
Ṣatunkọ aworan ti o wa tẹlẹ nipa fifi kun tabi rọpo awọn eroja nipasẹ itọka atẹle
Ṣiṣẹ gẹgẹbi ipilẹ ipilẹ iwadi ti o ṣe afihan itọnisọna ti ko ni iyasọtọ lu itọsọna CLIP fun titete
Ojo iwaju ti Awoṣe Itankale GLIDE
GLIDE funrararẹ jẹ itan-akọọlẹ pupọ, ti o rọpo nipasẹ DALL-E 2, Imagen, ati Itankale Stable, ṣugbọn awọn imọran rẹ tẹsiwaju nibi gbogbo. Itọnisọna-ọfẹ Classifier jẹ bọtini aiyipada fun iṣowo ni pipa iṣotitọ ati oniruuru, ati kikun-iwakọ ọrọ jẹ boṣewa bayi. Awọn ọna ṣiṣe iwaju n tọju awọn iṣeto itoni isọdọtun, idinku awọn ohun elo ti o fa itọnisọna to lagbara, ati fa awọn ipilẹ kanna si fidio ati itankale 3D, nitorinaa ipa GLIDE ju awoṣe lọ.
Fifi o sinu iwa
Kini idi ti o ṣe pataki
- Iyara ati iwọn. Visual AI le ṣe adaṣe adaṣe, wiwa, ati awọn iṣẹ ṣiṣe taagi ni iwọn.
- Kọ awọn yiyan. Awọn ẹgbẹ ẹda le ṣe apẹrẹ awọn imọran yiyara pẹlu awọn atunyẹwo afọwọṣe diẹ.
- Ẹgbẹ ati ṣiṣan iṣẹ. Awọn iṣẹ ṣiṣe le lo aworan ati awọn ifihan agbara fidio ti o nira tẹlẹ lati ṣiṣẹ.
Ṣọra fun
- Awọn ẹtọ aworan ati igbanilaaye le di awọn eewu labẹ ofin ti o ba jẹ afihan.
- Iṣe awoṣe le yatọ kọja ina, awọn ẹda eniyan, ati awọn agbegbe.
- Awọn idaniloju eke le ma ṣe akiyesi ayafi ti a ba ṣe abojuto awọn ala igbẹkẹle.
Next awọn igbesẹ
- Ṣetumo awọn ibeere gbigba fun pipe, iranti, ati awọn idiyele aṣiṣe.
- Ṣe idanwo pẹlu data ti o baamu awọn ipo iṣelọpọ gidi.
- Ṣafikun atunyẹwo eniyan fun igbẹkẹle kekere tabi awọn asọtẹlẹ ipa-giga.
- Tọpinpin awoṣe ki o ṣe tunṣe lẹhin kamẹra tabi awọn ayipada datasetto.
Tesiwaju Ṣiṣawari
Ìwé ìròyìn ọfẹ
Gba ìkànìyàn AI ojoojúmọ́
Ìtàn AI mẹta tó jẹ́rìí ní gbogbo owurọ́ ọjọ́ iṣẹ́, kọ́wé ní Gẹ̀ẹ́sì tó rọrùn. Ọfẹ́ fún gbogbo àkókò, kò sí ìpolówó.
Ìmeèlì kan ní gbogbo ọjọ́ iṣẹ́. Yọkúrò ní ìkànìyàn ní ìkànìyàn kan. A kò ta tàbí pín àdírẹ́sì rẹ.
Ṣe idanwo fun ara rẹ
Take the GLIDE Diffusion Model quiz
Ìdáhùn lẹ́sẹ̀kẹsẹ̀ lórí gbogbo ìdáhùn, àti iwe-ẹ̀rí tó lè pin pẹ̀lú ID tó lè jẹ́rìí lẹ́yìn tí o bá kọ́ ẹ̀kọ́.
Ṣe àtìlẹ́yìn ẹ̀kọ́ AI ọfẹ́. AI Understanding jẹ́ àjọ àìní èrè 501(c)(3) — kò sí ìpolówó, kò sí àkúnya owó, ní gbogbo àkókò. Ṣe ẹbun kan
Awọn ibeere ti a beere nigbagbogbo
Kini awoṣe GLIDE Diffusion?
GLIDE jẹ arosọ OpenAI awoṣe itankale ọrọ-si-aworan ti o ṣe afihan awọn itọsi pẹlu 'itọnisọna-ọfẹ classifier' le lu awọn eto orisun-GAN tẹlẹ. O jẹ okuta igbesẹ bọtini kan lori ọna si DALL-E 2.
Ọna itọsọna wo ni GLIDE rii ti o ṣe agbejade dara julọ, awọn aworan oloootitọ diẹ sii?
GLIDE ṣe afihan itoni-ọfẹ classifier funni ni ojulowo diẹ sii ati awọn abajade ibamu-dara ju itọsọna CLIP lọ.
What size did the published full GLIDE base diffusion model have, before counting its upsampler?
The full research model used a 3.5-billion-parameter base diffusion model with a separate upsampling stage.
Bawo ni itoni-ọfẹ classifier ṣiṣẹ lakoko ikẹkọ?
Nipa ikẹkọ lori awọn itọsi gidi ati ofo, awoṣe kọ ẹkọ iran ti ko ni ijẹẹmu, lẹhinna ṣe afikun laarin wọn ni iṣapẹẹrẹ.
Which later system describes its diffusion decoder as modifying the GLIDE architecture in the DALL-E 2 research paper?
The paper describes adding CLIP-image conditioning to a modified GLIDE architecture for its unCLIP decoder; this is a concrete architectural relationship.
Kilode ti OpenAI ṣe tusilẹ diẹ nikan, ẹya ti glide ti a yan ni gbangba?
OpenAI dawọ awoṣe kikun lori awọn ifiyesi ilokulo ati tujade titọ, iyatọ kekere dipo.
Tesiwaju kikọ
Jẹmọ awọn itọsọna
Awọn itọsọna diẹ sii ti a yan fun koko yii