Text To Image Generation On Cub

Metrics

FID

Results

Performance results of various models on this benchmark

Model Name	FID	Paper Title	Repository
TLDM	6.72	Truncated Diffusion Probabilistic Models and Diffusion-based Adversarial Auto-Encoders
Attention-driven Generator (perceptual loss)	-	Controllable Text-to-Image Generation
MirrorGAN	-	MirrorGAN: Learning Text-to-image Generation by Redescription
GALIP	10.08	GALIP: Generative Adversarial CLIPs for Text-to-Image Synthesis
GAWWN	67.22	Learning What and Where to Draw	-
AttnGAN	-	AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks
AttnGAN+CL	16.34	Improving Text-to-Image Synthesis Using Contrastive Learning
VQ-Diffusion-F	10.32	Vector Quantized Diffusion Model for Text-to-Image Synthesis
Lafite	10.48	LAFITE: Towards Language-Free Training for Text-to-Image Generation
StackGAN-v2	15.3	StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks
Swinv2-Imagen	9.78	Swinv2-Imagen: Hierarchical Vision Transformer Diffusion Models for Text-to-Image Generation	-
VQ-Diffusion-S	12.97	Vector Quantized Diffusion Model for Text-to-Image Synthesis
StackGAN-v1	51.89	StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks
DM-GAN	-	DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis
RAT-Diffusion	6.36	Data Extrapolation for Text-to-image Generation on Small Datasets	-
StackGAN	-	StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks
VQ-Diffusion-B	11.94	Vector Quantized Diffusion Model for Text-to-Image Synthesis
RAT-GAN	10.21	Recurrent Affine Transformation for Text-to-image Synthesis
DM-GAN+CL	14.38	Improving Text-to-Image Synthesis Using Contrastive Learning
DF-GAN	-	DF-GAN: A Simple and Effective Baseline for Text-to-Image Synthesis

0 of 20 row(s) selected.