Run latest ComfyUI Workflows on the cloud
Access powerful AI models and run complex workflows. No setup required – just sign in and start creating.
branding-product-shot-with-seeddream-v4-dual-input
An image-to-image workflow based on the latest Seedream-v4. Upload an image of your product with your logo, and the model will overlay your branding label or logo on the product.
Qwen-Image-Edit Try-On
A basic Try-on and image-to-image workflow using Qwen-Image-Edit, fast using distilled lora #i2i
WAN2.2 Image-to-Video with Radial-Attention
Generate videos from an image using WAN2.2. Take advantage of Radial Attention Speed-Ups to generate videos over 20 seconds in length in almost half the time.
Basic Text-to-Image with the HunyuanImage-2.1 Model
Text-to-image generation with Hunyuan Image 2.1. This model offers superior native resolution and text adherence thanks to its glyph encoder and integrated MLLM with Dual stream DiT architecture #t2i #hunyuanimage
Try-On (Nano-Banana)
Upload your subject and the garment type, and some prompt, get the subject wearing the clothes
Game Guide with Layout (Nano-Banana)
With this pack, you can switch tasks and produce a mockup for a strategy guide, including a way to upload your own border design with a second image
Through the ages Grid (Nano-Banana)
Photo Restoration (Nano-Banana)
Restore colorize and enhance old pictures
Insta Pic (Nano-Banana)
Upload a photo and type a location and let nan-banana make a picture for your socials
Character Template (Nano-Banana)
A workflow to streamline character design, upload one reference and a style, and get poses, expressions and color variations
Figurine 3D (Nano-Banana)
Create realistic Figurine sculptures from your image reference with nano-banana (Bring your own OpenRouter key)
Strategy Guide (Nano-Banana)
Upload your character or prop and create a strategy guide (Bring your own OpenRouter Key)
Infinite Avatar Lean Fast
Creates a video with a monologue from a provided audio and an image with Infinite WAN
Video_Restoration_Potato_to_HD
Infinite Avatar
A talking avatar image-to-video workflow named "Infinite Avatar" that dynamically generates animated avatars from a still image and audio input, utilizing an LLM for prompt generation. It employs a WanVideo model, multiple LoRAs, and MultiTalk with Wav2Vec models for audio processing and realistic speech synchronization.
BANANA
Recreate a Movie still with "Nano-Banana." You need a GEMINI_API_KEY to use this workflow. The generations are free, but Google cuts most people by location or during times of high demand
3d-product-qwen-image
Use a 3D model or image to generate a product ad or even generate a pseudo 3d render for a 3d model
3d-product-qwen-image-edit
Create ad images for products by passing your 3d object and a simple prompt
vOICE cLONER CHATTS
Clone a voice and make it read the provided text with
Dual Qwen-Edit
Experimental Dual Input (works well in some use-cases) use two images to control the edit
Top ComfyUI Workflows
Discover the most popular workflows created by our community
First & Last Frame i2v WAN2.2 (Native)
A basic image-to-video workflow where you provide the first and last frames as reference images, and the model will fill in the in-between animation. #i2v #flf #wan22
Text to Video WAN2.2 (Native)
A basic Text-to-Video workflow that generates a video based on your text prompt using WAN2.2 and the fast lightning LoRAs in just 4 to 7 steps. #t2v #wan22
Qwen-Image-Edit (Native)
Say goodbye to tedious manual edits! With Qwen’s powerful AI image editing workflow, you can transform images effortlessly using simple text instructions #i2i #edit
Qwen-Image Outpaint (Native)
Go beyond the edges: AI generates coherent extensions of your image based on context. No cropping needed—grow your scene. #i2i #outpainting #qwenimage
Qwen-Image Inpainting (Native)
Take control of your image: mask any area, and let AI reconstruct it exactly how you want. No Photoshop skills needed. #inpainting #i2i #qwenimage
Flux LoRAs (Native)
Flux LoRAs are small but mighty models that inject custom styles or characters into any model. LoRAs enable the customization of a model to generate new concepts or styles. #t2i #LoRA #Flux
Flux Text-To-Image (Native)
The simplest way to start with AI image generation: type a prompt, watch art emerge, powered by probabilistic sampling and smart denoising. #t2i #Flux
Flux Depth ControlNet (Native)
Depth maps are beneficial for separating elements based on camera proximity, allowing for a higher degree of change while maintaining structure. #i2i #depth #controlnet