ComfyUI_examples
Flux Examples
Flux is a family of diffusion models by black forest labs
For the easy to use single file versions that you can easily use in ComfyUI see below: FP8 Checkpoint Version
Regular Full Version
Files to download for the regular version
If you don’t have t5xxl_fp16.safetensors or clip_l.safetensors already in your ComfyUI/models/clip/ directory you can find them on: this link. You can use t5xxl_fp8_e4m3fn.safetensors instead for lower memory usage but the fp16 one is recommended if you have more than 32GB ram.
The VAE can be found here and should go in your ComfyUI/models/vae/ folder.
Tips if you are running out of memory:
Use the single file fp8 version that you can find by looking Below
You can set the weight_dtype in the “Load Diffusion Model” node to fp8 which will lower the memory usage by half but might reduce quality a tiny bit. You can also download the example.
Flux Dev
You can find the Flux Dev diffusion model weights here. Put the flux1-dev.safetensors file in your: ComfyUI/models/diffusion_models/ folder.
You can then load or drag the following image in ComfyUI to get the workflow:
Flux Schnell
Flux Schnell is a distilled 4 step model.
You can find the Flux Schnell diffusion model weights here this file should go in your: ComfyUI/models/unet/ folder.
You can then load or drag the following image in ComfyUI to get the workflow:
Simple to use FP8 Checkpoint version
Flux Dev
You can find an easy to use checkpoint for the Flux dev here that you can put in your: ComfyUI/models/checkpoints/ directory.
This file can be loaded with the regular “Load Checkpoint” node. Make sure you set CFG to 1.0 when using it.
Note that fp8 degrades the quality a bit so if you have the resources the official full 16 bit version is recommended.
You can then load or drag the following image in ComfyUI to get the workflow:
Flux Schnell
For Flux schnell you can get the checkpoint here that you can put in your: ComfyUI/models/checkpoints/ directory.
You can then load or drag the following image in ComfyUI to get the workflow:
Flux Extras
The following examples might require that you have some of the regular flux files that you can find links to at the top of this page.
Fill (Inpainting) model
Download the flux1-fill-dev.safetensors model file and put it in your ComfyUI/models/diffusion_models/ folder.
Here is an example you can drag in ComfyUI for inpainting, a reminder that you can right click images in the “Load Image” node and “Open in MaskEditor”.
Here is an example for outpainting:
Redux
The Redux model is a model that can be used to prompt flux dev or flux schnell with one or more images.
Download the sigclip_vision_patch14_384.safetensors model and put it in your ComfyUI/models/clip_vision folder and download the flux1-redux-dev.safetensors and put it in your ComfyUI/models/style_models folder.
You can then load or drag the following image in ComfyUI to get the workflow:
Canny and Depth
They are published in two versions, full model format: flux1-canny-dev.safetensors and flux1-depth-dev.safetensors, put them in your ComfyUI/models/diffusion_models/ folder
Here is an example for the full canny model:
They are also published in lora format that can be applied to the flux dev model: flux1-canny-dev-lora.safetensors and flux1-depth-dev-lora.safetensors, put them in your ComfyUI/models/loras/ folder
Here is an example for the depth lora.
Community Flux Controlnets
XLab and InstantX + Shakker Labs have released Controlnets for Flux. You can find the InstantX Canny model file here (rename to instantx_flux_canny.safetensors for the example below), the Depth controlnet here and the Union Controlnet here.
The XLab controlnets can be found here here.
Put these files under ComfyUI/models/controlnet directory.
Try an example Canny Controlnet workflow by dragging in this image into ComfyUI.
If you need an example input image for the canny, use this. Put it under ComfyUI/input.
