bytonylee / apisr
bytonylee / agent-demo-vietnam
bytonylee / hyper-flux
bytonylee / hyper-sd15
bytonylee / hyper-sd3
bytonylee / slam
bytonylee / cogview-v3-plus
CogView3: Finer and Faster Text-to-Image Generation via Relay Diffusion
bytonylee / perflow
PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator
bytonylee / stable-diffusion-3.5-large
bytonylee / stable-diffusion-3.5-medium
bytonylee / auraflow-v1
AuraFlow: Fully open-sourced flow-based text-to-image generation model
bytonylee / auraflow-v2
AuraFlow: Fully open-sourced flow-based text-to-image generation model
bytonylee / auraflow-v3
AuraFlow: Fully open-sourced flow-based text-to-image generation model
bytonylee / janus
bytonylee / meissonic
Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis
bytonylee / phi-3.5-vision-4.2b
bytonylee / qwen-vl-7b
bytonylee / pixtral-12b
bytonylee / aria-25.3b-moe
bytonylee / paligemma-3b-ft-448
bytonylee / molmo-7b-d
bytonylee / minicpm-v2.6
bytonylee / deepseek-vl-1.3b
bytonylee / flux-upscaler
bytonylee / kolors
Kolors: Effective Training of Diffusion Model for Photorealistic Text-to-Image Synthesis
bytonylee / playground-v2
Playground v2.0: A diffusion-based text-to-image generation model trained from scratch by the research team at Playground
bytonylee / stable-cascade
Würstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion Models
bytonylee / tcd-sdxl
Trajectory Consistency Distillation: Improved Latent Consistency Distillation by Semi-Linear Consistency Function with Trajectory Mapping
bytonylee / lightning-sdxl
SDXL-Lightning: Progressive Adversarial Diffusion Distillation
bytonylee / flash-sdxl
Flash Diffusion: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation
bytonylee / dmd2
Improved Distribution Matching Distillation for Fast Image Synthesis
bytonylee / sdxl-turbo
Adversarial Diffusion Distillation
bytonylee / pcm
Phased Consistency Model
bytonylee / lcm
Latent Consistency Models: Synthesizing High-Resolution Images with Few-step Inference
bytonylee / hyper-sdxl
Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis
bytonylee / tile-upscaler
bytonylee / magnific
bytonylee / real-esrgan
bytonylee / fooocus
bytonylee / instant-style-control
Free Lunch towards Style-Preserving in Text-to-Image Generation by InstantX team, with ControlNet
bytonylee / instant-style
Free Lunch towards Style-Preserving in Text-to-Image Generation by InstantX team
bytonylee / profile-avatar
bytonylee / playground-v2.5
Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation
bytonylee / honeybee
Locality-enhanced Projector for Multimodal LLM
bytonylee / imp
a family of multimodal small language models
bytonylee / moondream
Tiny vision language model