Average Model Cost: $0.0145
Number of Runs: 244,619
Models by this creator
Tortoise-tts is a text-to-audio model that allows users to generate speech from text and clone voices from mp3 files. It is an implementation of the Tacotron2 model and can be trained on large datasets to improve the quality of generated speech. The model is suitable for various applications such as voice assistants, audiobook narration, and speech synthesis in general.
The clip-guided-diffusion model is a text-to-image generation model that uses a denoising diffusion model. It can generate images based on input text by utilizing the CLIP pre-trained model. However, the inference process for this model is slower compared to other methods.
Retrieval-augmented-diffusion is a model that generates 768px images from text using computer vision techniques. It leverages the concept of diffusion models to generate high-quality images based on input text descriptions. The model utilizes a retrieval system to select relevant image patches to assemble the final image, resulting in accurate image generation.
Laionide-v4 is a GPT-4-based model that is trained to generate images from text descriptions. It uses a combination of human images and experimental style prompts to create visually appealing and realistic images. The model combines natural language processing with image generation techniques to produce image outputs based on the given text inputs.
The glid-3-xl model is a text-to-image model that has been fine-tuned for inpainting. It is based on the latent diffusion text2im model and is designed for computer vision tasks. It can generate images based on textual descriptions and is specifically trained to fill in missing parts of an image.
The sd-aesthetic-guidance model is an image-to-image model that uses stable diffusion and aesthetic CLIP embeddings to enhance and improve the aesthetic quality of images. It generates more visually appealing outputs by leveraging the aesthetic guidance of CLIP embeddings, ensuring that the generated images align with desired aesthetic attributes. This model can be helpful in various applications where aesthetics are important, such as image editing and enhancement.