Asronline
Models by this creator
sdxl-mk1
7
The sdxl-mk1 model is designed to generate Mortal Kombat 1 fighters and character skins. It is a specialized model created by asronline that is similar to other SDXL-based models like mk1-redux, masactrl-sdxl, sdxl-akira, and sdxl-mascot-avatars. These models offer a range of capabilities, from generating classic Mortal Kombat fighters to producing cute mascot avatars. Model inputs and outputs The sdxl-mk1 model accepts a variety of inputs, including a prompt, image, and various parameters to control the output. The outputs are generated images depicting Mortal Kombat 1 fighters and character skins. Inputs Prompt**: The input prompt that describes the desired output image. Image**: An input image that can be used as a starting point for the generation process. Mask**: An input mask that can be used to define areas of the image that should be preserved or inpainted. Seed**: A random seed value that can be used to control the randomness of the generated output. Width and Height**: The desired dimensions of the output image. Refine**: The refinement style to use when generating the output. Scheduler**: The scheduler algorithm to use when generating the output. LoRA Scale**: The scale factor for LoRA (Local Reparameterization) additions. Num Outputs**: The number of output images to generate. Refine Steps**: The number of refinement steps to perform. Guidance Scale**: The scale factor for classifier-free guidance. Apply Watermark**: A flag to control whether a watermark is applied to the output images. High Noise Frac**: The fraction of high noise to use for expert ensemble refinement. Negative Prompt**: An optional negative prompt to guide the generation process. Prompt Strength**: The strength of the input prompt when using image-to-image or inpainting. Num Inference Steps**: The number of denoising steps to perform during the generation process. Outputs Output Images**: The generated Mortal Kombat 1 fighter and character skin images. Capabilities The sdxl-mk1 model is capable of generating high-quality images of Mortal Kombat 1 fighters and character skins. It can produce a wide variety of characters and styles, and the input parameters allow for fine-tuning the output to match specific preferences. What can I use it for? The sdxl-mk1 model can be used to create custom Mortal Kombat 1-inspired artwork, character designs, or even fan projects. Potential use cases include generating content for games, websites, social media, or other Mortal Kombat-themed applications. The model's capabilities could also be leveraged to create unique and engaging marketing materials or merchandise for Mortal Kombat fans. Things to try With the sdxl-mk1 model, you can experiment with different prompts, input images, and parameter settings to see how they affect the generated output. Try describing specific Mortal Kombat characters or themes, or use the image-to-image and inpainting capabilities to refine or modify existing Mortal Kombat-inspired artwork. The model's flexibility allows for a wide range of creative possibilities.
Updated 10/4/2024
mk1-redux
1
The mk1-redux model is a refined version of the original MK1 model created by asronline, with a focus on generating fighters with human faces and different materials like water, ice, and fire. It is similar to other AI models like gfpgan, which is a practical face restoration algorithm for old photos or AI-generated faces, and edge-of-realism-v2.0, which can generate new images from any input text. Model inputs and outputs The mk1-redux model accepts a variety of inputs, including an input image for img2img or inpaint mode, a prompt, and optional parameters like seed, width, height, and scheduler. The model outputs one or more generated images that match the provided prompt. Inputs Prompt**: The input text prompt that describes the desired image Image**: An input image for img2img or inpaint mode Mask**: An input mask for inpaint mode, where black areas will be preserved and white areas will be inpainted Seed**: A random seed, which can be left blank to randomize Width/Height**: The desired width and height of the output image Refine**: The refine style to use Scheduler**: The scheduler algorithm to use LoRA Scale**: The LoRA additive scale, applicable only on trained models Num Outputs**: The number of images to output Refine Steps**: The number of steps to refine, for the base_image_refiner Guidance Scale**: The scale for classifier-free guidance Apply Watermark**: Whether to apply a watermark to the output image High Noise Frac**: The fraction of noise to use for the expert_ensemble_refiner Negative Prompt**: An optional negative prompt to guide the image generation Outputs One or more generated images that match the provided prompt Capabilities The mk1-redux model can be used to generate a variety of images, with a focus on fighters with human faces and different materials. It can be used for creative projects, concept art, and even commercial applications where high-quality, customized images are needed. What can I use it for? The mk1-redux model can be useful for a wide range of applications, such as creating concept art for games or films, generating custom product images for e-commerce websites, or even producing unique artwork for personal or commercial use. The model's ability to generate images with different materials and human-like faces makes it particularly versatile. Things to try One interesting thing to try with the mk1-redux model is experimenting with the different refine styles and scheduler algorithms to see how they affect the generated images. You could also try combining the model with other AI tools, such as the gfpgan model, to further enhance the realism and quality of the generated images.
Updated 10/4/2024