Maswali yanayounganishwa na mwongozo · Kati Kiwango

Maswali ya Muundo wa Usambazaji wa GLIDE

Gundua kizazi na uchoraji unaoongozwa na maandishi wa GLIDE, mafunzo ya masharti, sampuli zisizo na uainishaji, na usanifu wake wa kihistoria.

Njia za mwongozo zinazohusianaMfano wa Usambazaji wa Glide
Swali 1 ya 8

Je, ni njia gani ya mwongozo ambayo GLIDE ilipata kuwa inazalisha picha bora na za uaminifu kwa haraka?

Hakiki kila swali8 maswali

Majibu na maelezo huonekana unapojibu maswali.

  1. Je, ni njia gani ya mwongozo ambayo GLIDE ilipata kuwa inazalisha picha bora na za uaminifu kwa haraka?
    • Mwongozo usio na uainishaji
    • Mwongozo wa CLIP
    • Hakuna mwongozo
    • Kuhariri kwa mikono
  2. What size did the published full GLIDE base diffusion model have, before counting its upsampler?
    • About 3.5 thousand parameters
    • About 350 billion parameters
    • About 3.5 billion parameters
    • No trainable parameters
  3. Je, mwongozo usio na uainishaji hufanya kazi vipi wakati wa mafunzo?
    • Mtindo huo huona tu onyesho sahihi
    • Kiainishi tofauti cha picha kinafunzwa pamoja
    • Vidokezo vinatafsiriwa kwa nambari bila mpangilio
    • Mfano wakati mwingine huona haraka ya kweli na wakati mwingine tupu
  4. Which later system describes its diffusion decoder as modifying the GLIDE architecture in the DALL-E 2 research paper?
    • The original text-only GPT-2 model
    • The unCLIP system associated with DALL-E 2
    • The Whisper speech recognizer
    • The CLIP contrastive encoder alone
  5. Kwa nini OpenAI ilitoa toleo dogo tu, lililochujwa la GLIDE hadharani?
    • Mfano kamili ulipotea
    • Iliendeshwa tu kwenye kompyuta kubwa
    • Wasiwasi kuhusu matumizi mabaya ya jenereta yenye nguvu ya picha
    • Leseni kutoka kwa mtu wa tatu
  6. Je, GLIDE iliunga mkono kipengele gani cha uhariri?
    • Uchoraji unaoendeshwa na maandishi
    • Unukuzi wa sauti
    • Miundo ya lahajedwali
    • Utoaji wa video
  7. How did GLIDE's upsampler complement its base text-conditioned diffusion model?
    • It replaced the text prompt with an audio transcript
    • It increased the resolution of the image produced by the base model
    • It converted the image into the training tokenizer's vocabulary
    • It supplied manual labels for every generated object
  8. At GLIDE sampling time, how does classifier-free guidance strengthen prompt conditioning?
    • It retrains the model weights after every generated pixel
    • It requires a separate class-label classifier to score every step
    • It replaces the conditional prediction with the unconditional one
    • It combines conditional and unconditional predictions, extrapolating toward the conditional one