Diffusion model
flux1-dev. safetensors
FLUX.1 Dev · Diffusion model for ComfyUI
- File
flux1-dev.safetensors- Type
- Diffusion model
- Size
- 23.8 GB
- Folder
ComfyUI/models/diffusion_models/- Source
- Comfy-Org/Flux-1-Dev
- SHA-256
4610115bb0c8…
3 workflows use this file
What is Flux1 Dev?
Flux1 Dev is a diffusion model, the core network that turns your prompts into the output. You can run it locally in ComfyUI with full control over every parameter, or access it through Comfy Cloud. ComfyUI's node-based workflow editor lets you connect Flux1 Dev with other models and custom nodes to build any pipeline you need. There are 3 official ComfyUI workflow templates that use Flux1 Dev, ready to load and customize.
Read the full tutorial →Workflows for this file
- Flux, Flux.1
Flux.1 Dev: Text to Image
Uses this file - Flux.1, Flux
Flux.1 Dev fp8: Text to Image
Uses this file - Flux.1, Flux
Flux.1 Redux Model
Uses this file - Flux, Flux.1
Flux.1 Inpaint
- Flux, Flux.1
Flux.1 Dev USO Reference Image Generation
- Flux.1, Flux
Flux.1 Outpaint
- Flux.1, Flux
Flux.1 Dev OneReward
- Flux.1, Flux
Flux.1 Schnell Full: Text to Image
Frequently Asked Questions
Flux1 Dev is a diffusion model, the core network that turns your prompts into the output. You can run it locally in ComfyUI with full control over every parameter, or access it through Comfy Cloud. ComfyUI's node-based workflow editor lets you connect Flux1 Dev with other models and custom nodes to build any pipeline you need. There are 3 official ComfyUI workflow templates that use Flux1 Dev, ready to load and customize.
Follow the step-by-step tutorial at https://docs.comfy.org/tutorials/flux/flux-1-text-to-image. You can also load any of the 3 official ComfyUI workflow templates that use Flux1 Dev directly in ComfyUI.
There are 3 official ComfyUI workflow templates that use Flux1 Dev. Each template is ready to run in ComfyUI and can be customized to suit your project.
ComfyUI is free and open source. Flux1 Dev weights are available to download from Hugging Face. You only pay for compute when running on Comfy Cloud; local inference on your own hardware is always free.