Image transformer with text
Transforming images with text. Based on StyleGAN and CLIP
Transforming images with text. Based on StyleGAN and CLIP
Adding new objects to the image, generating new images, creating objects with sketching and segmentation map, upscaling resolution
This is a Cog implementation of the Real-ESRGAN super-resolution model from ruDALL-E
Removing background on images using image segmentation model
Edit portraits. Change gaze direction, nose form, makeup, skin, age, emotions and 10+ other parameters of face.
Convert any text typed on the keyboard or internet text into a kind of scan or photo of your handwritten homework. Choose a background (16 available) and a font (54 different fonts are available), Insert text and click “Create homework”, then you can download the handwritten homework in the form of a photo or pdf.
Create and Browse generative AI art created by other users
Platform that helps artists train AI to create images in their own style
⚡ Lightning-fast Dreambooth finetuning. Train Stable Diffusion models in minutes. Scale up to 1000s of runs per day. With dreamlook.ai, you can train for example 1’200 steps in 3 minutes, or 10’000 steps in 15 minutes.
Calculating % of whether description fit the given image. Match text to an already pre-trained image encoder.