About Flux download
Suggest downloading models separately according to different workflows rather than directly downloading the corresponding model files in the table.If you want to use Flux.1 in ComfyUI, you need to upgrade to the latest ComfyUI version. If you haven’t updated ComfyUI yet, you can follow the articles below for upgrading or installation instructions.Original version Flux.1 ComfyUI workflow guideThe original version workflow is more complex, requiring installation of multiple files. This tutorial includes two parts:Download and install CLIP、VAE、UNET modelsFlux.1 original version complex workflow, including Dev and Schnell versions, as well as low-memory version workflow examplesPart 1: Download and install CLIP、VAE、UNET modelsDownload ComfyUI flux_text_encoders clip modelsComfyUI flux_text_encoders on hugging faceDownload clip_l.safetensorsDownload t5xxl_fp8_e4m3fn.safetensors or t5xxl_fp16.safetensors Depend on your VRAM and RAMPlace downloaded model files in folder.Note: If you have used SD 3 Medium before, you might already have the above two modelsDownload FLux.1 VAE ModelFLUX.1-schnell on hugging faceDownloaded the model.Place downloaded model files in folder.For identification, you can rename it to ;Download FLux.1 UNET ModelFLUX.1-schnell on hugging faceDownloaded the Place downloaded model files in folderPart 2: Flux.1 ComfyUI Original Workflow ExampleComfyUI offical Flux.1 workflow example: can just save the image and load into Comfy!Flux Dev ComfyUI workflow exampleFlux Schnell ComfyUI workflow ExampleFlux under 12GB VRAM ORG FP8 Checkpoint versionThe following Checkpoint models are provide by ComfyUI Org，you only need to download one model file, and you can use it directly.Download the model version you needPlace in You can also use the Kijia Flux-FP8 ,since the file names are similar, it is recommended to rename the file after downloading or create a separate folder to distinguish it.Flux dev FP8 Checkpoint version workflow exampleFlux Schnell FP8 Checkpoint version workflow exampleNF4 Version Flux.1 WorkflowAuthor: lllyasvielFirst, you need to install the corresponding plugin: installation instructions can be found at ComfyUI Plugin Installation GuideNF4 Version Model Downloadlllyasviel made two versions of the NF4 Flux model, please download the V2 version directly, this version has better details and effectsInstall the ComfyUI_bitsandbytes_NF4 plugin, if you don’t know how to install the plugin, you can refer to ComfyUI Plugin Installation GuideDownload the flux1-dev-bnb-nf4-v2 file, and place the downloaded file in the directoryNF4 Version Flux.1 Workflow ExampleGGUF Version Flux.1 WorkflowAuthor: City96Project Address: Plugins and Download ModelsDownload the Flux GGUF dev model or the Flux GGUF schnell model and place the model files in the directory.Download t5-v1_1-xxl-encoder-gguf, and place the model files in the directory.Download clip_l.safetensors and place the model files in the directory.Download ae.safetensors and place the model files in the directory, and rename it to .Install ComfyUI-GGUF plugin, if you don’t know how to install the plugin, you can refer to ComfyUI Plugin Installation GuideGGUF Version Flux.1 Workflow ExampleRun Flux.1 onlineHere are some online methods provided by Black Forest Labs for utilizing
Key features of the Flux download that are enabled through these drivers include:
- Qualitek No Clean Flux - Fluxes - somersetsolders.com
- FLUX:: Analyzer - Analyze This! - FLUX:: Immersive
- Keyboard Shortcuts in Flux - Flux - Documentation
- FLUX Beambox Pro - FLUX USA
- What is Heat Flux? (Thermal Flux)
- Flux Charger (Black) - Flux Chargers
- FLUX Beam Studio - FLUX Europe
We have listed all the Flux based workflows(IP Adpater, ControlNets, LoRAs) at one place so that you don't need to jump to multiple articles.As instructed by Xlabs, you need to use the Flux Dev official model released by Black Forest Labs that uses the Unet loader. This helps to handle large Flux models (FP16 variant). They provided other option to work with lower end GPUs. You can also use Flux GGUF variant to manage 12GB VRAM memory usage. To use the Flux GGUF model variant, into the workflow you need to replace the "Load Diffusion Model" node with "UNET loader(GGUF)" node. You can find the "UNET Loader" from bootleg category.We already covered all the Flux variants in our previous tutorials. To get into the workflows (provided below), first of all you need to install ComfyUI on your machine and get the Flux model installation. You can also checkout other better options like Flux Tools released by Black Forest Labs.Table of Contents:Initial SetupTo setup IP Adpater, ControlNet or LoRA for Flux, you need to clone the Xlabs repository. Move to "ComfyUI/custom_nodes" folder and navigate to folder address location and type "cmd" to open command prompt. The do the repository cloning, use the cloning command:git clone IP AdapterThe IP-Adapter for Flux Dev released by X-Labs. The model has been trained on 512 by 512 for 50k steps that means we have the flexibility to use 512 by 512 and 1024 by 1024 resolution for image generation.Installation:1. Now, you need to update custom nodes. Move into "ComfyUI/custom_nodes/x-flux-comfyui" folder. Double click to open "setup.py" file to start the update process. Restart ComfyUI. After this, you have to download models.2. Download the IP Adapter model from Xlabs Hugging Face repository, and save it inside "ComfyUI/models/xlabs/ipadapters" folder.3. Next, you have to download Clip-L model(model.safetensors) from OpenAI's HuggingFace, and save this to "ComfyUI/models/clip_vision" folder. Rename it to anything relevant to get easily identified. 4. Workflows can be found inside your "ComfyUI/custom_nodes/x-flux-comfyui/workflows" folder or it can be downloaded from Xlab's Github repository.5. Now to work with the workflow, use these nodes - Flux Load IPAdapter and Apply Flux
