환쟁이vs딸깍충 자강두천
구독자 28010명
알림수신 355명
유머글을 공유하는 채널입니다. 정치·잡담·혐오 금지. 이슈글은 이슈 글머리 준수해주세요.
이슈(유머/정보)
요즘 트짹 그림계 근황
추천
92
비추천
10
댓글
63
조회수
9040
작성일
댓글
[63]
gtsgtagts
ㅇㅇ
슬쩍눈팅하려다심연에잠식됨
Gamcho
ㅇㅇ
Gamcho
ㅇㅇ
ㅁㅁㅁㅁ
비추수집가
ㅁㅁㅁㅁ
비추수집가
ㅁㅁㅁㅁ
풍신귀댕이
촉로
아콩
불판러
파편1
강달달
ㅇㅇ
생선빌런
물감고아보면못참는사람
shin
미러
shin
미러
shin
쀼부붑
유령함대
익명A
A4쥬지
JohnSmith
shin
우횻
shin
우횻
shin
우횻
pqu
shin
DeltaLaboratory
arXiv.org
High-Resolution Image Synthesis with Latent Diffusion Models
By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a guiding mechanism to control the image generation process without retraining. However, since these models typically operate directly in pixel space, optimization of powerful DMs often consumes hundreds of GPU days and inference is expensive due to sequential evaluations. To enable DM training on limited computational resources while retaining their quality and flexibility, we apply them in the latent space of powerful pretrained autoencoders. In contrast to previous work, training diffusion models on such a representation allows for the first time to reach a near-optimal point between complexity reduction and detail preservation, greatly boosting visual fidelity. By introducing cross-attention layers into the model architecture, we turn diffusion models into powerful and flexible generators for general conditioning inputs such as text or bounding boxes and high-resolution synthesis becomes possible in a convolutional manner. Our latent diffusion models (LDMs) achieve a new state of the art for image inpainting and highly competitive performance on various tasks, including unconditional image generation, semantic scene synthesis, and super-resolution, while significantly reducing computational requirements compared to pixel-based DMs. Code is available at https://github.com/CompVis/latent-diffusion .
버번워커
ㅇㅇ
Ellie
소코반10000
ㅇㅇ
아마우아코
solidro
One_way
singularity
A4쥬지
AttackHeat
gjj
고경민씨
ㅇㅇ
trskktfaq
수릍
JohnSmith
망치와몰루
마에스트라
플라이하이
ㅇㅇ
ㅇㅇ
고경민씨
본 게시물에 댓글을 작성하실 권한이 없습니다.
로그인 하신 후 댓글을 다실 수 있습니다. 아카라이브 로그인
최근
최근 방문 채널
최근 방문 채널