cog-flux
C
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.
Total Visits: 474.6M
Top Region: US(19.34%)
Website Views : 55.8K
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
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase