Conditional Text-to-Image Synthesis
6 papers with code • 2 benchmarks • 1 datasets
Introducing extra conditions based on the text-to-image generation process, similar to the paradigm of ControlNet.
Benchmarks
These leaderboards are used to track progress in Conditional Text-to-Image Synthesis
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
COCO-MIG
Most implemented papers
BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion
As such paired data is time-consuming and labor-intensive to acquire and restricted to a closed set, this potentially becomes the bottleneck for applications in an open world.
GLIGEN: Open-Set Grounded Text-to-Image Generation
Large-scale text-to-image diffusion models have made amazing advances.
Late-Constraint Diffusion Guidance for Controllable Image Synthesis
Specifically, we train a lightweight condition adapter to establish the correlation between external conditions and internal representations of diffusion models.
Prompt-Free Diffusion: Taking "Text" out of Text-to-Image Diffusion Models
shi-labs/prompt-free-diffusion
•
•
Text-to-image (T2I) research has grown explosively in the past year, owing to the large-scale pre-trained diffusion models and many emerging personalization and editing approaches.
InstanceDiffusion: Instance-level Control for Image Generation
frank-xwang/InstanceDiffusion
•
•
Text-to-image diffusion models produce high quality images but do not offer control over individual instances in the image.
MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis
limuloo/migc
•
•
Lastly, we aggregate all the shaded instances to provide the necessary information for accurately generating multiple instances in stable diffusion (SD).
