Kediska Tafatirka Feejignaanta Toosan ee degdega ah

Jawaabaha iyo sharraxaadaha waxay soo baxayaan markaad qaadanayso kediska.

1. Waa maxay macluumaadka gudaha ee degdega ah-si-degdegga ah uu dib u isticmaalo si uu u ilaaliyo goobta?
   • Khariidadaha fiiro-dhaafka ah ee isku xidha erayada gobollada sawirka
   • pixels soo saarka ugu dambeeya
   • Xaaladda wanaajinta moodeelka
   • Xog-ururinta sawirka
2. Deg-deg-degdegga ma u baahan tahay hagaajinta qaabka?
   • Haa, dib u tabobar buuxa tafatirkiiba
   • Maya, waa farsamo bilaa tababar ah
   • Haa, laakiin kaliya codeeyaha qoraalka
   • Kaliya ku darista ereyo cusub
3. Si aad 'baaskiil' ugu beddelato 'mootada' intaad goobta ilaalinayso, habka:
   • Gacan ku dabool gobolka baaskiilka
   • Waxay ku tababartaa LoRA cusub mootooyinka
   • U fiirso dareenka u dhexeeya calaamadaha u dhigma ee labada dareen
   • Waxay abuurtaa muuqaal madax-bannaan oo dhammaystiran
4. Maxaa dib-u-cusboonaynta dareenka calaamaduhu ku guulaysataa?
   • Waxay beddeshaa xallinta sawirka
   • Waxay tirtirtaa gebi ahaanba calaamadda
   • Waxay dib u habaysaa erayada degdega ah
   • Waxay xoojisaa ama daciifisaa saamaynta aragga eraygaas
5. Markaad kelmad ku darto degdegga, degdeg u-deji:
   • Waxay ilaalisaa dareenka calaamadaha aan isbeddelin waxayna u ogolaataa calaamadda cusub oo keliya inay samaysato dareen cusub
   • Dib-u-randomizes sawirka oo dhan
   • Way iska indho tirtay ereyga lagu daray
   • U beddelo qaab sal oo ka duwan
6. Which separate model was trained to follow written image-editing instructions from an input image?
   • InstructPix2Pix, a conditional diffusion editor trained on generated instruction-edit pairs
   • Prompt-to-Prompt, which edits by controlling cross-attention maps during denoising
   • Null-text inversion, which optimizes unconditional embeddings for image inversion
   • LocalBlend, which creates a selected-token mask from attention maps
7. What does the Prompt-to-Prompt LocalBlend feature use to localize a change?
   • A hand-drawn mask required for every Prompt-to-Prompt edit
   • The EXIF metadata of the original image
   • Attention maps for selected prompt words to construct a spatial mask
   • A classifier that identifies image copyright
8. What extra step can enable Prompt-to-Prompt editing of a real photograph?
   • Train a new diffusion model from scratch
   • Convert the photograph into an audio spectrogram
   • Replace every cross-attention layer with a classifier
   • Invert the image into the diffusion model’s latent trajectory first