Sign In

🌌 Flux Dev 2 Reboot Workflow + FlashVSR Upscaler

Updated: Nov 26, 2025

base model

Type

Workflows

Stats

165

0

Reviews

Published

Nov 26, 2025

Base Model

Flux.2 D

Hash

AutoV2
F511483BD9
default creator card background decoration
Vionex's Avatar

Vionex

The FLUX.1 [dev] Model is licensed by Black Forest Labs. Inc. under the FLUX.1 [dev] Non-Commercial License. Copyright Black Forest Labs. Inc.

IN NO EVENT SHALL BLACK FOREST LABS, INC. BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.

⚑ Minimal β€’ Clean β€’ Organized β€’ Ready-to-Use

A minimal, extremely clean ComfyUI workflow for FLUX.2-dev Reboot paired with a FlashVSR upscaler and an Original vs Upscaled comparison panel β€” designed for fast, professional image generation.


πŸ“ Description

πŸ”₯ What this workflow does

This workflow is built to give you a simple, non-cluttered way to generate images using FLUX.2-dev (Reboot) and instantly upscale them using FlashVSR β€” all inside one single neat setup.

Most FLUX workflows become spaghetti…
This one is clean, compact, and beginner-friendly while still being creator-grade.


πŸ”§ Pipeline Overview

🟦 1. FLUX.2-dev Generation (Reboot Block)

  • Uses FLUX.2-dev GGUF main model

  • External Mistral 3 Small Text Encoder

  • External Flux VAE

  • Organized nodes for prompt, seed, settings

  • Large dedicated preview for the base render

πŸŸͺ 2. FlashVSR Upscale Block

  • Direct upscale from Flux output

  • Supports 2Γ— / 4Γ— depending on VRAM

  • Clean routing with minimal node clutter

  • Perfect for 4K-ready results

🟨 3. Original vs Upscaled Preview (Side-by-Side)

  • Built-in viewers for comparison

  • Quickly check detail, noise, sharpness

  • No need to save & re-import images


πŸ“¦ Required Models

🧠 Main FLUX.2-dev GGUF

πŸ”— https://huggingface.co/orabazes/FLUX.2-dev-GGUF/tree/main

✍️ Text Encoder (Mistral 3 Small for Flux)

πŸ”— https://huggingface.co/Comfy-Org/flux2-dev/blob/main/split_files/text_encoders/mistral_3_small_flux2_fp8.safetensors

🎨 Flux VAE

πŸ”— https://huggingface.co/Comfy-Org/flux2-dev/tree/main/split_files/vae

πŸ”Ό Upscaler

βœ” FlashVSR model + ComfyUI FlashVSR node
(Download through ComfyUI Manager or GitHub repo)

Please place models in correct folders based on your ComfyUI setup.


πŸš€ How to Use

  1. Open the workflow in ComfyUI

  2. Enter your prompt + negative prompt

  3. Choose your resolution / steps

  4. Generate with Flux Dev 2

  5. The output is automatically sent to FlashVSR

  6. Compare results in the Original vs Upscaled panel

  7. Export sharp, clean images instantly

Super simple, super fast.


πŸ’» Recommended Settings

  • GPU: 10–12GB VRAM recommended

  • Base resolution: 1024Γ—1024, 832Γ—1216, or 1216Γ—832

  • Steps: 20–30 (ideal for Flux)

  • FlashVSR:

    • 2Γ— upscale β†’ safe for all GPUs

    • 4Γ— upscale β†’ best quality, higher VRAM needed


🎯 Best For

✨ Concept art
✨ Portraits
✨ Thumbnails
✨ Posters / Key Visuals
✨ Fast client work
✨ Clean templates for custom pipelines


πŸ™ Credits

🧩 FLUX.2-dev GGUF β€” orabazes
🧠 Flux VAE + Text Encoder β€” Comfy-Org
πŸ“ˆ FlashVSR β€” FlashVSR authors + ComfyUI integration
🎨 Workflow assembly, optimization & layout β€” (Veonix)