Guide-yakabatana mibvunzo · Pakati Nhanho

GigaGAN Yakasimudzwa Jenareta Quiz

Ongorora GigaGAN's text-conditioned architecture, generation speed, multi-scale discriminator, latent editing, uye patsanura high-resolution upsampler.

Nzira dzekutungamira dzinoenderanaGigagan Yakasimudzwa Jenareta
Mubvunzo 1 ye 8

What total parameter count did the paper report for one high-capacity GigaGAN framework configuration?

Tarisa mubvunzo wese8 mibvunzo

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

  1. What total parameter count did the paper report for one high-capacity GigaGAN framework configuration?
    • 1.0 billion total across the 652.5M base generator and 359.1M upsampler
    • 70 million total across a 64M generator and 6M discriminator
    • 1.0 billion in the base generator alone, with no upsampler
    • 3.5 billion total across two text encoders
  2. Ndeipi yakakura yekumhanyisa mukana weGigaGAN pamusoro pekupararira modhi?
    • Izvo hazvidi GPU
    • Iyo inogadzira chifananidzo mune imwechete yekupfuura nhanho pane akawanda denoising matanho
    • Inodzidzira mune imwe sekondi
    • Iyo haishandisi neural network
  3. Ko GigaGAN's 'sample-adaptive kernel selection' inoitei?
    • Inodzima mapikisi asina kushandiswa
    • Inodzvanya mufananidzo kuJPEG
    • Inosanganisa bhanga remasefa ekuchinja uchishandisa huremu hunobva pamashoko ekukurumidza
    • Inotora iyo GPU otomatiki
  4. GigaGAN inobatanidza sei ruzivo rwemashoko mukugadzirwa kwemifananidzo?
    • Nekudzvanya chirevo
    • Iyo inofuratira zvinyorwa zvachose
    • Nokudhinda zvinyorwa pamufananidzo
    • Kuburikidza nekutarisisa-kutarisisa mameseji emeddings uye kuenzanisa CLIP maficha
  5. Ndeipi yekuwedzera kugona iyo GigaGAN inopa kupfuura base chizvarwa?
    • Yakasiyana GAN upsampler inogona kusvika 4K resolution
    • Audio synthesis
    • Kuzivikanwa kwekutaura
    • Database querying
  6. Sei GigaGAN's latent nzvimbo inobatsira pakugadzirisa maturusi?
    • Haikwanise kupepetwa
    • Inotsigira kududzira kwakatsetseka uye kusanganiswa kwemaitiro kuitira shanduko inodzoreka
    • Inongochengeta zvinyorwa chete
    • Inobvisa mufananidzo mushure mekushandiswa kumwe chete
  7. How does GigaGAN’s image discriminator make predictions across resolutions?
    • It scores only the text prompt and ignores generated images
    • It predicts one label at the final resolution only
    • It receives an image pyramid and predicts real or fake at multiple input and downsampling scales
    • It compares generated images with a fixed set of training captions only
  8. What does GigaGAN’s base generator produce for later multi-scale processing?
    • A single class label for the entire image
    • A sequence of text tokens for an autoregressive decoder
    • Only the final upsampled image, with no intermediate scales
    • An image pyramid with outputs at several resolutions