Improved techniques for training score-based generative models
- https://proceedings.neurips.cc/paper/2020/file/92c3b916311a5517d9290576e3ea37ad-Paper.pdf
- 2020, 1112회 인용
SCORE-BASED GENERATIVE MODELING THROUGH STOCHASTIC DIFFERENTIAL EQUATIONS
- 21/2
- https://arxiv.org/pdf/2011.13456
- 5240
DALL-E : Zero-Shot Text-to-Image Generation
- 21/2
- https://arxiv.org/pdf/2102.12092
- 5100
Diffusion Models Beat GANs on Image Synthesis
Stable Diffusion : High-Resolution Image Synthesis with Latent Diffusion Models
Elucidating the Design Space of Diffusion-Based Generative Models
- https://proceedings.neurips.cc/paper_files/paper/2022/file/a98846e9d9cc01cfb87eb694d946ce6b-Paper-Conference.pdf
- 2022, 1503회 인용
CLASSIFIER-FREE DIFFUSION GUIDANCE
- 22/7
- https://arxiv.org/pdf/2207.12598
- 3100
GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
- 22/3
- https://arxiv.org/pdf/2112.10741
- 3164
DALL-E 2: Hierarchical Text-Conditional Image Generation with CLIP Latents
Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding
GLIGEN: Open-Set Grounded Text-to-Image Generation
- 23/1
- 281회 인용
- https://arxiv.org/pdf/2301.07093
PROGRESSIVE DISTILLATION FOR FAST SAMPLING OF DIFFUSION MODELS
- https://openreview.net/pdf?id=TIdIXIpzhoI
- 2022, 2
- 1000회 인용
DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps
- https://proceedings.neurips.cc/paper_files/paper/2022/file/260a14acce2a89dad36adc8eefe7c59e-Paper-Conference.pdf
- 2022, 6
- 1100회 인용
Variational Diffusion Models
- https://proceedings.neurips.cc/paper/2021/file/b578f2a52a0229873fefc2a4b06377fa-Paper.pdf
- 2021, 7
- 1100회 인용
2023 ~ diffusion 논문들
Adding Conditional Control to Text-to-Image Diffusion Models
- https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Adding_Conditional_Control_to_Text-to-Image_Diffusion_Models_ICCV_2023_paper.pdf
- https://openaccess.thecvf.com/content/ICCV2023/supplemental/Zhang_Adding_Conditional_Control_ICCV_2023_supplemental.pdf
- 2023, 2
- 3412 회 인용
- https://github.com/lllyasviel/ControlNet
- 31200 stars
Consistency Models
- https://arxiv.org/pdf/2303.01469
- 2023, 3
- 750회 인용
T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models
- https://arxiv.org/pdf/2302.08453
- 2023, 2
- 834회 인용
- https://github.com/TencentARC/T2I-Adapter
- 3500 stars
On Distillation of Guided Diffusion Models
- https://openaccess.thecvf.com/content/CVPR2023/papers/Meng_On_Distillation_of_Guided_Diffusion_Models_CVPR_2023_paper.pdf
- 2022, 10
- 436회 인용
Adversarial diffusion distillation
- https://arxiv.org/pdf/2311.17042
- 2023, 11
- 266회 인용
Guiding a Diffusion Model with a Bad Version of Itself
- 24, 6
- 14회 인용
- https://arxiv.org/pdf/2406.02507
- https://github.com/NVlabs/edm2
- 610 stars
ad_official