-
Boosting Latent Diffusion Models via Disentangled Representation Alignment
Paper • 2601.05823 • Published • 17 -
VQRAE: Representation Quantization Autoencoders for Multimodal Understanding, Generation and Reconstruction
Paper • 2511.23386 • Published • 16 -
Visual Generation Tuning
Paper • 2511.23469 • Published • 16 -
A Style is Worth One Code: Unlocking Code-to-Style Image Generation with Discrete Style Space
Paper • 2511.10555 • Published • 63
AI & ML interests
None defined yet.
Recent Activity
Papers
View all Papers-
Boosting Latent Diffusion Models via Disentangled Representation Alignment
Paper • 2601.05823 • Published • 17 -
VQRAE: Representation Quantization Autoencoders for Multimodal Understanding, Generation and Reconstruction
Paper • 2511.23386 • Published • 16 -
Visual Generation Tuning
Paper • 2511.23469 • Published • 16 -
A Style is Worth One Code: Unlocking Code-to-Style Image Generation with Discrete Style Space
Paper • 2511.10555 • Published • 63
spaces 9
pinned
Running on CPU Upgrade
10k
Kolors Virtual Try-On
👕
Generate a virtual try‑on image of a person wearing a garment
pinned
Running
Featured
906
Kolors Character With Flux
🤹
Kolors Character to keep character developed with Flux
pinned
Running
615
Kolors Portrait With Flux
🤗
Kolors Portrait to keep face identity developed with Flux
Build error
25
CoTyle
🎨
Generate images from text prompts
Build error
43
Kolors Controlnet and IP-Adapter-Plus
🌁
Runtime error
94
Kolors FaceID
🥸
models 9
Kwai-Kolors/CoTyle
Text-to-Image • Updated • 18 • 21
Kwai-Kolors/Kolors-ControlNet-Pose
Updated • 36 • 10
Kwai-Kolors/Kolors-IP-Adapter-FaceID-Plus
Text-to-Image • Updated • 1.44k • 64
Kwai-Kolors/Kolors-Inpainting
Text-to-Image • Updated • 66 • 63
Kwai-Kolors/Kolors-ControlNet-Depth
Text-to-Image • Updated • 36 • 21
Kwai-Kolors/Kolors-ControlNet-Canny
Text-to-Image • Updated • 56 • 23
Kwai-Kolors/Kolors-IP-Adapter-Plus
Text-to-Image • Updated • 1.41k • 118
Kwai-Kolors/Kolors
Text-to-Image • Updated • 592 • • 853
Kwai-Kolors/Kolors-diffusers
Updated • 2.34k • 111
datasets 0
None public yet