Konieshadow
Models by this creator
fooocus-api
1.6K
fooocus-api is a third-party Fooocus model created by konieshadow. Fooocus is an image generation software that takes inspiration from Stable Diffusion and Midjourney, providing an offline, open-source, and free alternative. fooocus-api provides a REST API for using the Fooocus model, allowing users to leverage its powerful image generation capabilities in any programming language. Similar models include fooocus-api-realistic and fooocus-api-anime, which are also third-party Fooocus models created by konieshadow with preset configurations for realistic and anime-style images, respectively. Additionally, the fooocus model by vetkastar and the txt2img model by fofr provide alternative image generation capabilities. Model inputs and outputs fooocus-api accepts a variety of inputs to control the image generation process, including prompts, image seeds, guidance scales, and ControlNet configurations for image prompting. The model can generate multiple images at once and supports features like upscaling, inpainting, and outpainting. Inputs Prompt**: The textual prompt that describes the desired image. Negative Prompt**: The textual prompt that describes what should not be included in the image. Image Seed**: The seed value used to generate the image. Guidance Scale**: The strength of the text conditioning during generation. Refiner Switch**: The strength of the refiner module during generation. Image Number**: The number of images to generate. Sharpness**: The sharpness of the generated images. Performance Selection**: The trade-off between image quality and generation speed. Aspect Ratios Selection**: The aspect ratio of the generated images. ControlNet Inputs and Configuration**: Optional inputs and settings for the ControlNet module, which can be used for image prompting, inpainting, and outpainting. Outputs Image URLs**: A list of URLs pointing to the generated images. Capabilities fooocus-api is capable of generating high-quality images based on textual prompts, with a focus on ease of use and automation. The model includes various optimization and quality improvement techniques that aim to provide a seamless user experience, reducing the need for manual tweaking compared to other image generation models. What can I use it for? fooocus-api can be used for a wide range of image generation tasks, from creating concept art and illustrations to generating custom images for various applications. Its accessible API design makes it easy to integrate into various projects, allowing developers to leverage its powerful capabilities in their own applications. Things to try You can experiment with different prompts, image seeds, and ControlNet configurations to explore the model's capabilities. Try generating images with different styles, genres, or subjects, and see how the model handles various input scenarios. Additionally, you can explore the model's inpainting and outpainting features to modify or expand existing images.
Updated 9/18/2024
fooocus-api-anime
605
fooocus-api-anime is a third-party Fooocus model with a preset for generating anime-style images. It is maintained by konieshadow. Fooocus is an image generation software that learns from Stable Diffusion and Midjourney, offering offline, open-source, and free capabilities. It automates various optimizations and quality improvements, allowing users to focus on prompts and images rather than technical parameters. Similar AI models include fooocus, which adds inpaint_strength and loras_custom_urls features, and animagine-xl-3.1, an anime-themed text-to-image Stable Diffusion model. The cog-a1111-ui model also provides a collection of anime Stable Diffusion models with VAEs and LORAs. Model inputs and outputs The fooocus-api-anime model accepts a variety of inputs for image generation, including prompts, image prompts, and various control parameters. The outputs are high-quality images in a URI format. Inputs Prompt**: The text prompt for image generation. Cn Img[1-4]**: Input images for image prompts. If all are None, image prompts will not be applied. Cn Stop[1-4]**: Stop values for the corresponding image prompts, with a range of 0 to 1. Cn Type[1-4]**: The ControlNet type for the corresponding image prompts, defaulting to "ImagePrompt". Cn Weight[1-4]**: The weight for the corresponding image prompts, with a range of 0 to 2. Sharpness**: The sharpness of the generated image, with a range of 0 to 30. Image Seed**: The seed used to generate the image, with -1 indicating a random seed. Image Number**: The number of images to generate, with a range of 1 to 8. Guidance Scale**: The guidance scale for image generation, with a range of 1 to 30. Refiner Switch**: The refiner switch value, with a range of 0.1 to 1. Negative Prompt**: The negative prompt for image generation. Uov Input Image**: The input image for upscaling or variation. Uov Method**: The method for upscaling or variation, defaulting to "Disabled". Uov Upscale Value**: The upscale value, used only when the Uov Method is "Upscale (Custom)". Inpaint Input Image**: The input image for inpainting or outpainting. Inpaint Input Mask**: The mask for inpainting. Inpaint Additional Prompt**: Additional prompt for inpainting. Outpaint Selections**: The outpainting selections, with literal values for "Left", "Right", "Top", and "Bottom" separated by commas. Outpaint Distance[Top/Left/Right/Bottom]**: The outpainting distance for the corresponding direction. Performance Selection**: The performance selection, defaulting to "Speed". Aspect Ratios Selection*: The aspect ratio selection for the generated image, defaulting to "1152896". Outputs Array of URIs**: The generated images in URI format. Capabilities The fooocus-api-anime model can generate high-quality anime-style images based on text prompts, image prompts, and various control parameters. It leverages the Fooocus software's optimizations and quality improvements to provide a user-friendly experience, allowing users to explore new mediums of thought and expand their imaginative powers. What can I use it for? fooocus-api-anime can be used for a variety of creative and artistic applications, such as: Generating anime-themed illustrations, character designs, and concept art. Creating visual assets for anime-inspired games, animations, or other multimedia projects. Exploring and expanding one's artistic imagination through the model's AI-powered image generation capabilities. Things to try With the fooocus-api-anime model, you can experiment with different prompts, image prompts, and control parameters to generate a wide range of anime-style images. Try combining various styles, such as "Fooocus V2" and "SAI Fantasy Art," to see how the model responds. You can also explore the model's inpainting and outpainting capabilities by providing input images and masks to create unique and dynamic compositions.
Updated 9/18/2024
fooocus-api-realistic
391
The fooocus-api-realistic is a third party Fooocus replicate model with the 'realistic' preset. It is developed and maintained by konieshadow. This model is similar to the fooocus-api-anime model, which has a preset for anime-style images. The Fooocus project aims to provide an easy-to-use image generation tool that learns from Stable Diffusion and Midjourney, allowing users to focus on prompts and images without needing complex technical parameters. Model inputs and outputs The fooocus-api-realistic model takes a variety of inputs to generate images, including a prompt, image seed, guidance scale, and various settings for image upscaling, inpainting, and outpainting. The model can generate up to 8 images at a time and supports features like ControlNet for blending images into the generation process. Inputs Prompt**: The text prompt that describes the desired image. Image Seed**: The seed used to generate the image, with -1 indicating a random seed. Guidance Scale**: The scale used to guide the image generation towards the provided prompt. Sharpness**: The sharpness level to apply to the generated images. Image Number**: The number of images to generate (up to 8). Negative Prompt**: The text prompt that describes undesired elements in the image. Style Selections**: The Fooocus styles to apply to the image generation. Performance Selection**: The performance mode to use, such as "Speed" or "Quality". Aspect Ratios Selection**: The aspect ratio of the generated images. ControlNet Inputs**: Optional input images and settings for ControlNet, which can blend the input images into the generation process. Outputs Generated Images**: The resulting images produced by the model, returned as a list of image URLs. Capabilities The fooocus-api-realistic model is capable of generating a wide variety of realistic-style images based on the provided prompts and settings. It can handle complex prompts, blend input images into the generation process, and produce high-quality results. The model's capabilities make it suitable for tasks like product visualization, scene generation, and creative exploration. What can I use it for? You can use the fooocus-api-realistic model to generate realistic-style images for a variety of applications, such as: Product Visualization**: Generate images of products or objects to showcase their design, features, and properties. Scene Generation**: Create realistic scenes and environments for use in games, movies, or other multimedia projects. Creative Exploration**: Experiment with different prompts and settings to explore new ideas and expand your creative horizons. Things to try Try experimenting with different prompts, image seeds, and ControlNet settings to see how they affect the generated images. You can also explore the various performance and aspect ratio options to find the best balance between speed and quality for your needs. Additionally, consider blending input images into the generation process using ControlNet to incorporate specific elements or styles into the final output.
Updated 9/18/2024