惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

量子位
Google DeepMind News
Google DeepMind News
爱范儿
爱范儿
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
NISL@THU
NISL@THU
T
Threat Research - Cisco Blogs
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
L
Lohrmann on Cybersecurity
V
Visual Studio Blog
Cyberwarzone
Cyberwarzone
D
Docker
The Hacker News
The Hacker News
C
CERT Recently Published Vulnerability Notes
Vercel News
Vercel News
Project Zero
Project Zero
S
Schneier on Security
aimingoo的专栏
aimingoo的专栏
I
Intezer
腾讯CDC
M
MIT News - Artificial intelligence
Hugging Face - Blog
Hugging Face - Blog
P
Palo Alto Networks Blog
C
CXSECURITY Database RSS Feed - CXSecurity.com
AWS News Blog
AWS News Blog
GbyAI
GbyAI
MongoDB | Blog
MongoDB | Blog
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
V
Vulnerabilities – Threatpost
G
Google Developers Blog
N
Netflix TechBlog - Medium
The Cloudflare Blog
Microsoft Security Blog
Microsoft Security Blog
Y
Y Combinator Blog
A
Arctic Wolf
S
Securelist
酷 壳 – CoolShell
酷 壳 – CoolShell
Cisco Talos Blog
Cisco Talos Blog
Recent Announcements
Recent Announcements
C
Cyber Attacks, Cyber Crime and Cyber Security
L
LINUX DO - 热门话题
T
Threatpost
Latest news
Latest news
Blog — PlanetScale
Blog — PlanetScale
Security Latest
Security Latest
Engineering at Meta
Engineering at Meta
大猫的无限游戏
大猫的无限游戏
H
Help Net Security
The GitHub Blog
The GitHub Blog
T
Tor Project blog
P
Proofpoint News Feed

Runpod Blog.

DeepSeek V4 in the wild, and how to run it on Runpod New Runpod datacenter now live: AP-IN-1 Track GPU spend across your team with Cost Centers The GPU supply supercycle is here. Here’s what AI builders need to know. Community Spotlight: One-click AI image and video generation on Runpod with SwarmUI | Runpod Blog Community Spotlight: LoRA Pilot Data Prep to Inference Introducing the Runpod Assistant: Manage Your Cloud GPU Resources with Natural Language OpenAI's Parameter Golf: Train the Best Language Model That Fits in 16MB on Runpod LLM inference optimization: techniques that actually reduce latency and cost Pruna P-Video and Vidu Q3 public endpoints now available on Runpod Runpod brand spelling guide Quickstart - Runpod Documentation The AI market looks nothing like the narrative Training StyleGAN3 with Vision-Aided GAN on Runpod KoboldAI – The Other Roleplay Front End, And Why You May Want to Use It How to Connect Cursor to LLM Pods on Runpod for Seamless AI Dev Community Spotlight: How AnonAI Scaled Its Private Chatbot Platform with Runpod Prompt Scheduling with Disco Diffusion on Runpod Runpod's Latest Innovation: Dockerless CLI for Streamlined AI Development Run Your Own AI from Your iPhone Using Runpod Introducing Flash: Run GPU workloads on Runpod Serverless: No Docker required Use Claude Code with your own model on Runpod: No Anthropic account required Avoid Errors by Selecting the Proper Resources for Your Pod What hackers built on Runpod at TreeHacks 2026 Easily Back Up and Restore Your Pod with Cloud Sync + Backblaze B2 The Complete Guide to GPU Requirements for LLM Fine-Tuning AI Guides, Tutorials & GPU Infrastructure Insights | Runpod Your first Claude Code project within Runpod: a complete setup guide 10 billion Serverless requests and counting Building for resilience: Runpod’s response to the AWS us-east-1 outage How to Connect Google Colab to Runpod Founder Series #1: The Runpod Origin Story AMD MI300X vs. NVIDIA H100: Mixtral 8x7B Inference Benchmark Run Llama 3.1 405B with Ollama on Runpod: Step-by-Step Deployment How to Run FLUX Image Generator with Runpod (No Coding Needed) How to Use 65B+ Language Models on Runpod Deploy Llama 3.1 with vLLM on Runpod Serverless: Fast, Scalable Inference in Minutes Open Source Video & LLM Roundup: The Best of What’s New Run vLLM on Runpod Serverless: Deploy Open Source LLMs in Minutes Introduction to vLLM and PagedAttention New update to Github integration: release rollback! | Runpod Blog A note to the developers who built Runpod with us Deploy ComfyUI as a Serverless API Endpoint Setting up Slurm on Runpod Clusters: A Technical Guide Building an OCR System Using Runpod Serverless From No-Code to Pro: Optimizing Mistral-7B on Runpod for Power Users Lessons While Using Generative Language and Audio For Practical Use Cases Runpod RoundUp 3 – AI Music and Stock Sound Effect Creation New Navigational Changes To Runpod UI Use alpha_value To Blast Through Context Limits in LLaMa-2 Models Runpod Roundup 5 – Visual/Language Comprehension, Code-Focused LLMs, and Bias Detection Runpod is Proud to Sponsor the StockDory Chess Engine Runpod Roundup 4 – Open Source LLM Evaluators, 3D Scene Reconstruction, Vector Search Meta and Microsoft Release Llama 2 as Open Source SuperHot 8k Token Context Models Are Here For Text Generation How to Manage Funding Your Runpod Account Encrypted Volumes on Runpod: Protect Your Data at Rest How to Run a "Hello World" on Runpod Serverless Runpod AI field notes: December 2025 Faster GitHub Builds: Major Performance Improvements to Our Automated Integration Partnering with Defined AI to Bridge the Data Wealth Gap How to Run Serverless AI and ML Workloads on Runpod How to fine-tune a model using Axolotl Transcribe and translate audio files with Faster Whisper Runpod Achieves SOC 2 Type II Certification: Continuing Our Compliance Journey Orchestrating GPU workloads on Runpod with dstack Exploring Runpod Serverless: Create Workers From Templates DeepSeek V3.1: A Technical Analysis of Key Changes from V3-0324 Deep Cogito Releases Suite of LLMs Trained with Iterative Policy Improvement Wan 2.2 Releases With a Plethora Of New Features Iterative Refinement Chains with Small Language Models The New Runpod.io: Clearer, Faster, Built for What’s Next Introducing Clusters: On-Demand Multi-Node AI Compute Run DeepSeek R1 on Just 480GB of VRAM How Do I Transfer Data Into My Runpod? Spot vs. On-Demand Instances: What’s the Difference? Deploy GitHub Repos to Runpod with One Click Run GGUF Quantized Models Easily with KoboldCPP on Runpod How to Work with GGUF Quantizations in KoboldCPP Introducing Better Forge: Spin Up Stable Diffusion Pods Faster Supercharge Your LLMs with SGLang: Boost Performance and Customization Mastering Serverless Scaling on Runpod: Optimize Performance and Reduce Costs RAG vs. Fine-Tuning: Which Is Best for Your LLM? Run Larger LLMs on Runpod Serverless Than Ever Before – Llama-3 70B (and beyond!) How to Run vLLM on Runpod Serverless (Beginner-Friendly Guide) Embracing New Beginnings: Welcoming Banana.dev Community to Runpod Stable Diffusion + ComfyUI on Runpod: Easy Setup Guide Runpod RoundUp 2 – 32k Token Context LLMs and New StabilityAI Offerings Runpod Roundup: High-Context LLMs, SDXL, and Llama 2 16k Context LLM Models Now Available On Runpod Savings Plans Are Here For Secure Cloud Pods – How To Purchase a Monthly Plan And Save Big Pygmalion-7b from PygmalionAI has been released, and it's amazing Ada Architecture Pods Are Here – How Do They Stack Up Against Ampere? Spin up a Text Generation Pod with Vicuna and Experience a GPT-4 Rival Using OpenPose to Annotate Poses Within Stable Diffusion Set Up a Chatbot with Oobabooga on Runpod Connect VSCode to Your Runpod Instance (Quick SSH Guide) Deploy a Stable Diffusion UI on Runpod in Minutes Google Colab Pro vs. Runpod: Best GPU Cloud for AI Workloads How to Run a GPU-Accelerated Virtual Desktop on Runpod
How to Run the FLUX Image Generator with ComfyUI on Runpod
Shaamil Karim · 2026-02-18 · via Runpod Blog.

What is Flux?

Flux is an innovative text-to-image AI model developed by Black Forest Labs that has quickly gained popularity among generative AI enthusiasts and digital artists. Its ability to generate high-quality images from simple text prompts sets it apart. The Flux 1 family includes three versions of their image generator models, each with its unique features:

  • Flux 1 Pro: Known for its superior image generation quality, Flux 1 Pro is accessible via APIs and excels in performance. While their pro version is not available for direct download, it provides the fastest and highest-quality output through their license.
  • Flux 1 Dev: This model is open-weight, allowing developers to freely explore and experiment with it. However, it is not designed for commercial purposes.
  • Flux 1 Schnell: The most user-friendly of the three, Flux 1 Schnell is open-source and can be found on platforms like Hugging Face. It's also the fastest model and only requires 4 steps to generate. It's perfect for personal projects and can be integrated with tools like Diffusers or Comfy UI.

Flux is a powerful AI tool for generating images, offering endless possibilities for creativity. Whether you’re a digital artist, content creator, or tech enthusiast, Flux provides a platform for artistic expression, realistic images and innovation in AI-driven image generation.

Collage of AI-generated Flux images including a whale over a city, a retro TV showing FLUX, and a robot at a chalkboard

What Makes Flux Stand Out?

Flux 1 distinguishes itself from other text-to-image models with a blend of speed, quality, and adaptability. Here's what makes it unique:

  • Incredible Speed: Flux 1 is remarkably fast, capable of generating high-quality images in less than 2 seconds. This speed is transformative for creators who need quick results, such as those in video production or live streaming.
  • Hybrid Architecture: The Flux 1 models utilize a hybrid architecture that combines the strengths of transformers and diffusion models. This integration enables Flux to deliver exceptional image quality and processing speed, making it versatile for various creative projects.
  • Accurate Detail Rendering: A key feature of Flux is its ability to accurately render intricate details like fingers and text in images. This addresses common issues faced by other models, such as Stable Diffusion and DALL-E, using advanced transformer and diffusion techniques.

What is ComfyUI

ComfyUI is a popular graphical user interface (GUI) designed for creating and managing workflows in AI image generation. It allows users to construct image generation processes by connecting different modules, or nodes, in a flexible and intuitive way. This approach makes it easier for users to customize their workflows and explore different image generation techniques without needing to write complex code.

Although most popularly used to run Stable Diffusion, ComfyUI supports the integration of the FLUX image generation models.

If you'd like to try out Flux without ComfyUI and with Python code instead instead, check out our other blog on running the image generator using Jupyter notebook.

Try it for yourself

In this blog, we'll show you how you can get started with the Flux 1 Dev model and test out the AI image generator's visual quality with a sample text prompt in ComfyUI:

Prerequisites

  • Create your Runpod account (heads up, you'll need to load at least $10 into your Runpod account to get started).

Create Runpod account

Deploy Pod and Open ComfyUI

  1. Head to Pods and click Deploy.

Navigate to Deploy Pod in How to Run the FLUX Image Generator with ComfyUI

  1. Select Your GPU Configuration: Choose the GPU that best fits your needs and budget. For the Schnell and Dev versions, they could run on a L40 or RTX 4090 easily. However, you can opt for a more affordable GPU with lesser VRAM if that suits your requirements. For detailed guidance on selecting the right VRAM for your model, check out our blog on picking the right VRAM.

Deploy Pod in How to Run the FLUX Image Generator with ComfyUI

  1. Click Change Template, search for "Flux.1-Dev-ComfyUI by Camenduru", and click it. This template was created by one of our community members!

Change Template in How to Run the FLUX Image Generator with ComfyUI

4. Click the Deploy On-Demand button. It could take you up to 30 minutes to download the Flux models depending on your download speed! You can click Logs on your pod to track the download progress.

Runpod console logs for a Flux.1-Dev ComfyUI pod on an H100 showing the container image extracting

Logs Runpod in How to Run the FLUX Image Generator with ComfyUI

  1. Connect to Your Pod: Once deployed, navigate to the "Pods" section, locate your pod, and click "Connect."

Connect to Pod in How to Run the FLUX Image Generator with ComfyUI

  1. Click on Connect to HTTP Service [Port 7860] to open up ComfyUI

Connect to HTTP service port in How to Run the FLUX Image Generator with ComfyUI

Running Flux 1 on Comfy UI

Once you've opened up ComfyUI, follow these detailed instructions to generate images on Flux 1. If you click on Connect to HTTP Service [Port 7860] and see an error message, wait a few minutes and try again.

  1. Download Flux workflow: Follow the link to this github file by Cammenduru (the community member who created this template) and click the download button to the top right of the code block to access Flux 1.

GitHub view of the Flux.1-Dev-ComfyUI.json workflow file with the download button circled in red

2. Import workflow into ComfyUI: Navigate back to your ComfyUI webpage and click on Load from the list of buttons on the bottom right and select the Flux.1-Dev-ComfyUI.json file we downloaded in step 1.

3. Edit your prompt: Look for the query prompt box and edit it to whatever you'd like.

ComfyUI Flux workflow with the CLIP Text Encode prompt node circled, containing a robot painting prompt

  1. Run your model: Click Query Prompt to see your final high quality image like below! You can track the different modules and nodes in your workflow while it runs,.

ComfyUI in a browser with the Save Image node circled, showing a generated image of a robot painting

Woohoo! You just ran Flux 1 Schnell.

Comment below with any problems you may be facing for support – We're here to help you every step of the way!

Conclusion

Black Forest Labs' Flux represents a transformative leap in AI image generation, offering a powerful tool for artists, developers, and creators alike. With its integration into ComfyUI, Flux opens up new possibilities for real-time content creation, high-definition visuals, and output diversity, enabling users to easily generate high-quality images through a flexible and intuitive interface. Whether you're using the open source Flux Schnell for personal use in local development or integrating Flux Pro through APIs for high-quality commercial applications, this innovative model family offers unparalleled flexibility and quality in AI image generation.

As Black Forest Labs continues to push the boundaries of AI technology, Flux stands as a testament to the potential of open-source AI-driven creativity, paving the way for future innovations in AI image generators. While many other ai image generators like Stable Diffusion are meant for non-commercial use, Flux Schnell can be used to generate high quality images for commercial purposes with its Apache license. If you're ready to explore the capabilities of Flux through ComfyUI, head over to Runpod and unleash the full potential of this cutting-edge model in your own projects.

Deploy Flux on Runpod

Author profile: Shaamil Karim