Ikibazo gihuza ibibazo · Hagati Urwego

Ikibazo cya GigaGAN

Shakisha inyandiko ya GigaGAN yubatswe muburyo bwubaka, umuvuduko wibisekuru, ivangura rinini, ivangura ryihishwa, hamwe no gutandukanya ibyemezo bihanitse.

Inzira zijyanye no kuyoboraGigagan
Ikibazo 1 Bya 8

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

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  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. Ni ubuhe butumwa bukomeye bwihuta bwa GigaGAN kurenza moderi yo gukwirakwiza?
    • Ntabwo ikeneye GPU
    • Itanga ishusho mumurongo umwe wimbere aho kuba intambwe nyinshi zerekana
    • Itoza mu isegonda imwe
    • Ntabwo ikoresha urusobe rw'imitsi
  3. Niki GigaGAN 'sample-adaptive kernel selection' ikora?
    • Gusiba pigiseli idakoreshwa
    • Gabanya ishusho kuri JPEG
    • Kuvanga banki yo kwemeza muyunguruzi ukoresheje uburemere bukomoka kumyandiko
    • Hitamo GPU mu buryo bwikora
  4. Nigute GigaGAN yinjiza amakuru yinyandiko mugukora amashusho?
    • Mugukata ikibazo
    • Irengagiza inyandiko rwose
    • Mugucapura inyandiko kumashusho
    • Binyuze mu guhuza ibitekerezo kubyanditse no guhuza ibiranga CLIP
  5. Ni ubuhe bushobozi bw'inyongera GigaGAN atanga burenze ibisekuruza?
    • GAN upsampler itandukanye ishobora kugera kuri 4K imyanzuro
    • Guhindura amajwi
    • Kumenyekanisha imvugo
    • Kubaza Ububikoshingiro
  6. Kuki umwanya wihishe wa GigaGAN ufite akamaro kubikoresho byo guhindura?
    • Ntishobora guhindurwa
    • Ifasha interpolation yoroshye hamwe nuburyo bwo kuvanga impinduka zishobora kugenzurwa
    • Irabika inyandiko gusa
    • Isiba ishusho nyuma yo gukoreshwa
  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