

Cog Flux
Overview :
Cog inference for flux models is an inference engine for FLUX.1 [schnell] and FLUX.1 [dev] models, developed by Black Forest Labs. It supports compilation and quantization, sensitive content checks, and img2img support, aimed at enhancing the performance and safety of image generation models.
Target Users :
The target audience includes researchers and developers in the field of image generation, as well as users looking to enhance the performance and safety of image generation models.
Use Cases
Researchers using FLUX.1 [schnell] for image generation studies
Developers integrating the FLUX.1 [dev] model in personal projects
Content review teams using the checking feature to filter inappropriate content
Features
Compilation with torch.compile
Optional fp8 quantization based on aredden/flux-fp8-api
Content checks using CompVis and Falcons.ai
img2img support
Run the model on Replicate via API or browser
Serve as a template for custom FLUX.1
Run the model on personal hardware
How to Use
Select the model to run: FLUX.1 [schnell] or FLUX.1 [dev]
Use the command line tool to run the model for a single prediction
Run the model via the API of the Cog model or in a web browser
Read the Cog Getting Started guide to understand how Cog works
Consult the guide on how to push the model to Replicate
Customize the model as needed
Push the customized FLUX.1 model to Replicate
Featured AI Tools
Chinese Picks

Capcut Dreamina
CapCut Dreamina is an AIGC tool under Douyin. Users can generate creative images based on text content, supporting image resizing, aspect ratio adjustment, and template type selection. It will be used for content creation in Douyin's text or short videos in the future to enrich Douyin's AI creation content library.
AI image generation
9.0M

Outfit Anyone
Outfit Anyone is an ultra-high quality virtual try-on product that allows users to try different fashion styles without physically trying on clothes. Using a two-stream conditional diffusion model, Outfit Anyone can flexibly handle clothing deformation, generating more realistic results. It boasts extensibility, allowing adjustments for poses and body shapes, making it suitable for images ranging from anime characters to real people. Outfit Anyone's performance across various scenarios highlights its practicality and readiness for real-world applications.
AI image generation
5.3M