OpenFuture AI
All Ai Tools In One Place!
Detecting text on images and translating it
StyleGAN
0
Generating images and getting the video of generation process
LAIONIDE
0
Creating images from text. Results are a little more coherent and there are fewer (but not no) watermarks now.
Segmenting objects on a video and giving a text as an output.
Generating pixelated art based on text input
Generating images from text. This model takes as input a text prompt, and returns as an output the VQGAN latent space, which is then transformed into an RGB image. Eventually it minimizes the distance between the CLIP generated image features and the CLIP input text features.
Reconstructing a 3D human model from one photo
Fine-tuned Stable Diffusion model trained on 3d rendering. Use 'microworld render style' in the prompt.
