mrhan1993/fooocus-api
Generate images from text prompts. Guide generation with up to four image prompts via ControlNet (types: ImagePrompt, Fa...
Found 106 models (showing 61-80)
Generate images from text prompts. Guide generation with up to four image prompts via ControlNet (types: ImagePrompt, Fa...
Upscales and enhances image resolution using MultiDiffusion tiled diffusion method with ControlNet tile processing. Take...
Upscale and restore images from a single input image. Accept an image and an optional guiding text prompt, and output an...
Upscale low-resolution images to high-resolution images using a LoRA fine-tuned model. This model enhances image quality...
Upscale images up to 10x with optional face restoration. Accepts an input image and a scale factor, and returns a higher...
Upscale images up to 2× and restore facial details. Input an image and receive an upscaled image enhanced by Real-ESRGAN...
Upscales low-resolution images to higher resolutions using diffusion models for real-world image super-resolution. Takes...
Upscales images to higher resolutions using a Stable Diffusion 2.0 model fine-tuned specifically for image super-resolut...
Restore and enhance faces in photos and AI-generated images. Accepts an image and outputs an improved image with sharper...
Transform sketches into images. Accepts a sketch image and an optional text prompt; outputs a generated image. Control s...
Generate images from text prompts, fine-tuned for nature-themed content such as landscapes, forests, mountains, oceans,...
Super-resolves low-resolution ultra-wide video frames using wide-angle reference frames. Takes two image inputs - an LR...
Upscales images with high precision, specifically optimized for portraits, faces, and products. Features up to 10x faste...
Upscale and restore low-quality images. Takes an image input and returns a higher-resolution, artifact-reduced image wit...
Upscales images using Stable Diffusion with RiversHaveWings' approach, taking an input image and optional text prompt to...
Transform input images into photorealistic variations guided by a text prompt. Accepts an image (with optional prompt) a...
Swap one or two faces into a target image. Provide a target image and one or two source face images; optionally set user...
Upscales images using a Flux.1-dev ControlNet model trained with synthetic degradation data. Takes an input image and up...
Upscale and restore images from an input image up to 4x, removing noise, blur, and JPEG artifacts, with optional text-gu...
Upscale or downscale a grayscale image by a specified factor and return the resized image. Accepts an input image and a...