> ## Documentation Index
> Fetch the complete documentation index at: https://docs.comfy.org/llms.txt
> Use this file to discover all available pages before exploring further.

# FLUX.2 Dev image generation model (bfl/flux-2-dev): where to run it

> FLUX.2 Dev is a image generation model from Black Forest Labs. Run it with ComfyUI locally and Comfy Cloud; templates, files, nodes, and pricing.

Model ID: bfl/flux-2-dev
Provider: bfl
Product: local, cloud, workflows, nodes
Input: image, text
Output: image
License: open-weights

FLUX.2 Dev is a image generation model from Black Forest Labs. It takes image and text as input and produces image. It has open weights, so you can download the files and run it locally in ComfyUI.

## Where you can run it

| Where | Page | Use it when |
| - | - | - |
| ComfyUI (local or Comfy Cloud) | [FLUX.2 Dev in ComfyUI: Text-to-Image and Product Mockups](https://docs.comfy.org/tutorials/flux/flux-2-dev.md) | You follow a step-by-step workflow tutorial |
| ComfyUI (local or Comfy Cloud) | [FLUX.2 Klein in ComfyUI: Fast Text-to-Image and Editing](https://docs.comfy.org/tutorials/flux/flux-2-klein.md) | You follow a step-by-step workflow tutorial |
| Comfy Cloud | [Open `image_flux2` on Comfy Cloud](https://cloud.comfy.org/?template=image_flux2) | You want to run a ready-made workflow without installing anything |

## Model files for running it locally

Put each file in the matching folder under `ComfyUI/models/`. These come from the workflow templates below (workflow\_templates at `3c2199b9`).

| File | Folder | Download |
| - | - | - |
| `flux2_dev_fp8mixed.safetensors` | `models/diffusion_models/` | [Download](https://huggingface.co/Comfy-Org/flux2-dev/resolve/main/split_files/diffusion_models/flux2_dev_fp8mixed.safetensors) |
| `Flux_2-Turbo-LoRA_comfyui.safetensors` | `models/loras/` | [Download](https://huggingface.co/ByteZSzn/Flux.2-Turbo-ComfyUI/resolve/main/Flux_2-Turbo-LoRA_comfyui.safetensors) |
| `Flux2TurboComfyv2.safetensors` | `models/loras/` | [Download](https://huggingface.co/Comfy-Org/flux2-dev/resolve/main/split_files/loras/Flux2TurboComfyv2.safetensors) |
| `mistral_3_small_flux2_bf16.safetensors` | `models/text_encoders/` | [Download](https://huggingface.co/Comfy-Org/flux2-dev/resolve/main/split_files/text_encoders/mistral_3_small_flux2_bf16.safetensors) |
| `mistral_3_small_flux2_fp8.safetensors` | `models/text_encoders/` | [Download](https://huggingface.co/Comfy-Org/flux2-dev/resolve/main/split_files/text_encoders/mistral_3_small_flux2_fp8.safetensors) |
| `full_encoder_small_decoder.safetensors` | `models/vae/` | [Download](https://huggingface.co/black-forest-labs/FLUX.2-small-decoder/resolve/main/full_encoder_small_decoder.safetensors) |
| `flux2-vae.safetensors` | `models/vae/` | [Download](https://huggingface.co/Comfy-Org/flux2-dev/resolve/main/split_files/vae/flux2-vae.safetensors) |

## Workflow templates

| Template | Title | Added |
| - | - | - |
| `image_flux2` | FLUX.2 Dev | 2025-11-26 |
| `image_flux2_text_to_image` | FLUX.2 Dev Text to Image | 2025-11-26 |
| `image_flux2_fp8` | Product Mockup(FLUX.2 Dev FP8) | 2025-11-26 |
| `templates_all_in_one_image_edit_models.app` | 1 input and multiple editing model comparison | 2026-03-09 |
| `templates-all_in_one-image_edit_models` | 1 input and multiple editing model comparison | 2026-02-18 |

## Nodes

* [EmptyFlux2LatentImage](https://docs.comfy.org/built-in-nodes/EmptyFlux2LatentImage.md)
* [Flux2Scheduler](https://docs.comfy.org/built-in-nodes/Flux2Scheduler.md)
* [FluxGuidance](https://docs.comfy.org/built-in-nodes/FluxGuidance.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.