This is a simplified guide to an AI model called Aura-Flow maintained by Fofr. If you like these kinds of analysis, you should join AImodels.fyi or follow us on Twitter.
Model overview
AuraFlow is the largest completely open-sourced flow-based text-to-image generation model, developed by @cloneofsimo and @fal. It builds upon prior work in diffusion models to achieve state-of-the-art results on the GenEval benchmark. AuraFlow can be compared to other open-sourced models like SDXL-Lightning, Kolors, and Stable Diffusion, which all utilize different approaches to text-to-image generation.
Model inputs and outputs
AuraFlow is a text-to-image generation model that takes a text prompt as input and produces high-quality, photorealistic images as output. The model supports customization of various parameters like guidance scale, number of steps, image size, and more.
Inputs
- Prompt: The text description of the desired image
- Cfg: The guidance scale, controlling how closely the output matches the prompt
- Seed: A seed for reproducible image generation
- Shift: The timestep scheduling shift for managing noise in higher resolutions
- Steps: The number of steps to run the model for
- Width: The width of the output image
- Height: The height of the output image
- Sampler: The sampling algorithm to use
- Scheduler: The scheduler to use
- Output format: The format of the output images
- Output quality: The quality of the output images
- Negative prompt: Things to avoid in the generated image
Outputs
- Images: One or more high-quality, photorealistic images matching the input prompt
Capabilities
AuraFlow is capable of generating a ...
Top comments (0)