Trajectory Consistency Distillation: Improved Latent Consistency Distillation by Semi-Linear Consistency Function with Trajectory Mapping

Tiny vision language model

a family of multimodal small language models

Locality-enhanced Projector for Multimodal LLM

Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation

Free Lunch towards Style-Preserving in Text-to-Image Generation by InstantX team

Free Lunch towards Style-Preserving in Text-to-Image Generation by InstantX team, with ControlNet

Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis

Latent Consistency Models: Synthesizing High-Resolution Images with Few-step Inference

Phased Consistency Model

Adversarial Diffusion Distillation

Improved Distribution Matching Distillation for Fast Image Synthesis

Flash Diffusion: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation

SDXL-Lightning: Progressive Adversarial Diffusion Distillation

Würstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion Models

Playground v2.0: A diffusion-based text-to-image generation model trained from scratch by the research team at Playground

Kolors: Effective Training of Diffusion Model for Photorealistic Text-to-Image Synthesis

Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis

AuraFlow: Fully open-sourced flow-based text-to-image generation model

AuraFlow: Fully open-sourced flow-based text-to-image generation model

AuraFlow: Fully open-sourced flow-based text-to-image generation model