Papers with Code · CC BY-SA 4.0

Conditional Text-to-Image Synthesis

10-shot image generation › Text-to-Image Generation › Conditional Text-to-Image Synthesis 30 평가 기록 3 datasets

Introducing extra conditions based on the text-to-image generation process, similar to the paradigm of ControlNet.

논문

CheXGenBench: A Unified Benchmark For Fidelity, Privacy and Utility of Synthetic Chest Radiographs

2505.10496 2025-05-15 이 페이지의 평가 13건

FID (RadDino): 54.22

LaCon: Late-Constraint Diffusion for Steerable Guided Image Synthesis

2305.11520 2023-05-19 이 페이지의 평가 12건

FID: 20.27

BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion

2307.10816 2023-07-20 이 페이지의 평가 1건

instance success rate: 0.16mIoU: 0.26

GLIGEN: Open-Set Grounded Text-to-Image Generation

2301.07093 2023-01-17 이 페이지의 평가 1건

instance success rate: 0.30mIoU: 0.27

InstanceDiffusion: Instance-level Control for Image Generation

2402.03290 2024-02-05 이 페이지의 평가 1건

instance success rate: 0.51mIoU: 0.46

MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis

2402.05408 2024-02-08 이 페이지의 평가 1건

instance success rate: 0.66mIoU: 0.56

ReCo: Region-Controlled Text-to-Image Generation

2211.15518 2022-11-23 이 페이지의 평가 1건

instance success rate: 0.55mIoU: 0.49