Latent Consistency Models: Synthesizing High-Resolution Images with Few-step Inference
AuraFlow: Fully open-sourced flow-based text-to-image generation model
CogView3: Finer and Faster Text-to-Image Generation via Relay Diffusion
Improved Distribution Matching Distillation for Fast Image Synthesis
Flash Diffusion: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation
Locality-enhanced Projector for Multimodal LLM
Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis
a family of multimodal small language models
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
Kolors: Effective Training of Diffusion Model for Photorealistic Text-to-Image Synthesis
SDXL-Lightning: Progressive Adversarial Diffusion Distillation
Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis
Tiny vision language model
Phased Consistency Model
PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator
Playground v2.0: A diffusion-based text-to-image generation model trained from scratch by the research team at Playground
Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation
Adversarial Diffusion Distillation
This model is cold. You'll get a fast response if the model is warm and already running, and a slower response if the model is cold and starting up.
