HejuruUbuyobozi bukurikira
Amashusho ya AI Amashusho mubyiciro byubuhanzi
AI igaragara
Amabwiriza ya AI
GigaGAN is a text-to-image GAN architecture introduced by Adobe and collaborators in 2023.
Umva iki gitaboAI-byavuzwe · ~2 min
The paper reports 512px generation in about 0.13 seconds in its tested configuration and describes a separate GAN upsampler; speed and image-quality comparisons depend on resolution, hardware, and baseline.
GigaGAN, introduced by Adobe and researchers in 2023, addressed instability encountered when naively scaling earlier GAN architectures to large text-to-image datasets. The paper widens the generator and discriminator, uses sample-adaptive convolution filters, and incorporates cross-attention to text embeddings. The generator emits an image pyramid across multiple scales. The paper reports a 512px output in about 0.13 seconds and a 4096px output in about 3.7 seconds for the tested framework; the high-resolution pipeline uses the base generator with a separate GAN super-resolution model. Results apply to those reported configurations and do not establish that GigaGAN is faster than every diffusion model. The separate upsampler can also be applied to low-resolution inputs from other text-to-image systems. In one high-capacity framework configuration reported in the paper, the base generator has 652.5 million parameters and the separate upsampler has 359.1 million, for 1.0 billion total parameters across the two networks.
Gukora ishusho ya 512px uhereye kumyandiko isaba hafi icya cumi cyamasegonda kugirango igaragaze igishushanyo mbonera
Kuzamura ifoto ntoya ya 128px kumashusho ya 4K ukoresheje ishusho ya GAN ishingiye kuri super-resolution upsampler
Gutondekanya neza hagati yuburyo bubiri mu mwanya wihishe kugirango uhindure ubuzima, nkigikombe cya kawa kijya mu cyayi
Gukoresha uburyo bwo kuvanga kugirango ukomeze imiterere yikintu mugihe uhinduranya ibihangano byubuhanzi cyangwa amabara palette mubikoresho byo guhindura Adobe-buryo
GigaGAN yagaruye inyungu muri GANs nkibintu byihuta byihuta byo gukwirakwizwa, cyane cyane kubihe nyabyo kandi bigahinduka aho igisekuru kimwe gifite akamaro. Tegereza sisitemu ya Hybrid ikoresha amashanyarazi ya GAN muburyo bwo kureba ako kanya no gukwirakwiza kunonosorwa bwa nyuma, wongeyeho GAN upsamplers ihujwe no gushingira. Umwanya wacyo utagaragara kandi utuma ushimishwa nibikoresho byo kugenzura aho interpolation yoroshye ikubita buhoro buhoro.
Ibaruwa y'amakuru y'ubuntu
Inkuru eshatu zizewe za AI buri gitondo cy'iminsi y'akazi, zanditse mu rurimi rworoshye. Ubuntu iteka ryose, nta kwamamaza.
Imeri imwe buri munsi y'akazi. Kwiyimura mu buryo bumwe. Ntitwigera tugurisha cyangwa ngo dusangire aderesi yawe.
Isuzume
Ibisubizo ako kanya kuri buri kibazo, n'icyemezo gishobora gusangirwa gifite ID yagenzurwa umaze gutsinda isomo.
Fasha uburezi bwa AI bw'ubuntu. AI Understanding ni umuryango utegamiye kuri leta wa 501(c)(3) — nta kwamamaza, nta kwishyura, iteka ryose. Tanga impano
GigaGAN is a text-to-image GAN architecture introduced by Adobe and collaborators in 2023. The paper reports 512px generation in about 0.13 seconds in its tested configuration and describes a separate GAN upsampler; speed and image-quality comparisons depend on resolution, hardware, and baseline.
The paper reports a 652.5M-parameter base generator and a separate 359.1M-parameter upsampler, totaling 1.0B parameters across the framework.
The paper reports a single-pass 512px sample in about 0.13 seconds in its tested setup. The comparison with iterative diffusion depends on resolution, hardware, and the particular diffusion baseline.
Aho gushungura neza, GigaGAN ifata akayunguruzo kandi ikoresha inyandiko yashyizwemo uburemere no kuyihuza kuri sample, byongerera ubushobozi umutekano.
GigaGAN ikoresha guhuza ibitekerezo byanditse muri generator kandi igahuza amashusho yakozwe hamwe nibiranga inyandiko ya CLIP ikoresheje ivangura.
GigaGAN ikubiyemo GAN ishingiye kuri super-resolution upsampler ishobora guhindura ikintu gito mumashusho atyaye 4K.
Komeza wige
Abandi bayobozi batoranijwe kuriyi ngingo
HejuruUbuyobozi bukurikira
Amashusho ya AI Amashusho mubyiciro byubuhanzi
AI igaragara