Stable Diffusion XL Adapters
14 repos
Text-to-image generation models using adapter architectures with Stable Diffusion XL and the Hugging Face diffusers library. The cluster centers on T2I (text-to-image) adapters that condition image generation on various control signals—canny edge detection, sketch, line art, depth maps (via Midas and Zoe models), and OpenPose keypoints—enabling precise control over generated image composition and structure. Repositories here implement and distribute these adapter weights and inference code for controlled diffusion-based image synthesis.
diffusers ·2,461
text-to-image ·2,132
safetensors ·1,977
stable-diffusion-xl ·1,945
stable-diffusion-xl-diffusers ·1,940
controlnet ·1,213
text_to_image ·521
inpainting ·389
image-to-image ·334
t2i-adapter ·329
