AI, connected.
No code required.
The latest models. Chain them into workflows. Run instantly — or scale via API.
Build with Blocks
Chain PUW tools, Replicate models, and other workflows. Infinite combinations. Run & share via UI or API.
25+ PUW Tools
Interior AI, Video AI, 3D Gen, and more. All ready to chain together.
1000+ Replicate Models
SDXL, Stable Diffusion, LLaMA, and every open-source model you can imagine.
Workflow Inception
Use other creators' workflows as building blocks. They update, yours updates too.
Turn workflows intoapps
Transform your AI workflows into shareable applications. No code. One click publish.
Select Workflows
Choose from your workflows or community creations.
Pick a Theme
Minimal, Cards, or Showcase themes available.
Publish Instantly
One click to go live. Share your app URL anywhere.
Free to create
Explore AI Models
Run powerful AI models directly in your workflows. No setup required.
sdxl-lightning-4step
SDXL-Lightning by ByteDance: a fast text-to-image model that makes high-quality images in 4 steps
flux-schnell
The fastest image generation model tailored for local development and personal use
stable-diffusion
A latent text-to-image diffusion model capable of generating photo-realistic images given any text input
nano-banana
Google's latest image editing model in Gemini 2.5
sdxl
A text-to-image generative AI model that creates beautiful images
flux-kontext-pro
A state-of-the-art text-based image editing model that delivers high-quality outputs with excellent prompt following and consistent results for transforming images through natural language
flux-dev
A 12 billion parameter rectified flow transformer capable of generating images from text descriptions
flux-fast
This is the fastest Flux endpoint in the world.
controlnet-scribble
Generate detailed images from scribbled drawings
seedream-4
Unified text-to-image generation and precise single-sentence editing at up to 4K resolution
z-image-turbo
Z-Image Turbo is a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.
flux-1.1-pro-ultra
FLUX1.1 [pro] in ultra and raw modes. Images are up to 4 megapixels. Use raw mode for realism.
nano-banana-pro
Google's state of the art image generation and editing model 🍌🍌
flux-pro
State-of-the-art image generation with top of the line prompt following, visual quality, image detail and output diversity.
sdxl-emoji
An SDXL fine-tune based on Apple Emojis
proteus-v0.2
Proteus v0.2 shows subtle yet significant improvements over Version 0.1. It demonstrates enhanced prompt understanding that surpasses MJ6, while also approaching its stylistic capabilities.
kandinsky-2.2
multilingual text2image latent diffusion model
flux-kontext-max
A premium text-based image editing model that delivers maximum performance and improved typography generation for transforming images through natural language prompts
hidream-l1-fast
This is an optimised version of the hidream-l1 model using the pruna ai optimisation toolkit!
ideogram-v3-turbo
Turbo is the fastest and cheapest Ideogram v3. v3 creates images with stunning realism, creative designs, and consistent styles
recraft-v3
Recraft V3 (code-named red_panda) is a text-to-image model with the ability to generate long texts, and images in a wide list of styles. As of today, it is SOTA in image generation, proven by the Text-to-Image Benchmark by Artificial Analysis
any-comfyui-workflow
Run any ComfyUI workflow. Guide: https://github.com/replicate/cog-comfyui
imagen-4
Google's Imagen 4 flagship model
wan-2.2-i2v-fast
A very fast and cheap PrunaAI optimized version of Wan 2.2 A14B image-to-video
kandinsky-2
text2img model trained on LAION HighRes and fine-tuned on internal datasets
flux-dev-lora
A version of flux-dev, a text to image model, that supports fast fine-tuned lora inference
proteus-v0.3
ProteusV0.3: The Anime Update
imagen-4-fast
Use this fast version of Imagen 4 when speed and cost are more important than quality
realistic-vision-v5.1
Implementation of Realistic Vision v5.1 with VAE
p-image
A sub 1 second text-to-image model built for production use cases.
How it works
Building AI workflows should be as easy as connecting dots. We made it exactly that simple.
Upload
Drop your image or enter a prompt. That's all you need to start.
Chain
Connect AI models together like building blocks. Each output flows to the next.
Get Results
One click runs everything. Multiple AI tools, instant output.
Think of it like connecting apps, but for AI.
Creative AI Tools
Professional AI-powered tools for image generation, video creation, 3D modeling, and creative design workflows
Why PUW?
The complete AI workflow platform — visual building, instant hosting, and a marketplace to monetize.
| Feature | Replicate | ComfyUI | N8n | PUW |
|---|---|---|---|---|
| Visual workflow builder | ||||
| No code required | ||||
| Multi-model chaining | ||||
| Hosted infrastructure | ||||
| Built-in marketplace | ||||
| Creator revenue share | ||||
| One-click execution | ||||
| API access | ||||
| Community templates | ||||
| AI-native design |
Replicate
ComfyUI
N8n
PUW
PUW combines the power of ComfyUI with the simplicity of no-code — plus hosting and a marketplace to earn from your workflows.
Join the community
Creators and developers are building the future of AI workflows on PUW.
"PUW made it easy to chain AI models together. What used to take days now takes minutes."
"I built my first AI workflow without writing a single line of code. Game changer!"
"The visual builder is intuitive. I can experiment with different AI combinations quickly."
Want to build and earn?
Build AI workflows. Publish to the marketplace. Earn 70% of every run.
Growing community
Join creators building the future of AI workflows
Explore workflows
Discover and try AI workflows created by the community
No workflows found
Create First Workflow