demobook

ComfyUI: Generate and upscale images with Flux Kontext

ComfyUITry it →Watch full video →pixaroma ·

Demo summary

The creator demonstrates setting up a basic Flux Kontext workflow in ComfyUI, generating a character image, and then using a KSampler-based upscaler to increase resolution.

Step-by-step

  1. Load the fluxdev context model in the Load Diffusion Model node
  2. Configure the Dual Clip Loader with models that fit your video memory
  3. Set the Flux Conditioning to 2.5
  4. Connect a Conditioning Zero Out node to the negative prompt input
  5. Set the CFG to 1 to ignore the negative prompt
  6. Set the steps to 20 and choose a fixed seed for easier upscaling
  7. Run the workflow to generate the initial image
  8. Toggle the Fast Group Mutter node to enable the upscaler
  9. Adjust the Denoise values in the second KSampler to control how much the upscale differs from the original

Options

  • Use smaller clip models for lower-end video cards
  • Experiment with the step count settings
  • Delete or bypass the Clean Video RAM node if not needed
  • Use a random seed if you do not plan to upscale

Watch out for

  • CFG must be set to 1 because negative prompts are not supported
  • Upscaling to a larger size requires significantly more video memory
  • The first run is always slower due to model loading
  • The upscaler can sometimes produce a pixelated look, especially when editing an image

Tips

  • Use a fixed seed to ensure the upscaler works on the specific image you just generated
  • A Flux conditioning value of 2.5 is recommended over the usual 3.5
  • If you don't like the upscale result, run it again to get a new version
  • Change the first KSampler seed only when you want a completely new original image

Highlights

“It's pretty easy to use, but it needs more video memory to upscale to a larger size.”

All demos from “ComfyUI Tutorial Series Ep 52: Master Flux Kontext – Inpainting, Editing & Character Consistency”

  1. 2:432:38Generate and upscale images with Flux KontextCurrentThe creator demonstrates setting up a basic Flux Kontext workflow in ComfyUI, generating a character image, and then using a KSampler-based upscaler to increase resolution.ComfyUIAI Image Upscaler
  2. 7:201:48Edit image details with Flux KontextThe user shows how to load a reference image and use a text prompt to change specific features, such as changing a cartoon bunny's eye color to red.ComfyUIAI Inpainting
  3. 11:131:26Combine two images using Image StitchThe tutorial demonstrates using the Image Stitch node to combine two separate reference images (a woman and a bunny) into a single scene using Flux Kontext.ComfyUIAI Image Combiner
  4. 12:481:45Style transformation and line art conversionThe creator demonstrates transforming a portrait into a watercolor painting and converting a 3D-style bunny into a line art illustration using specific style prompts.ComfyUIAI Style Transfer
  5. 15:471:17Product branding and placementThe video shows how to take a logo or a product photo (perfume bottle) and use Flux Kontext to place it into a new, AI-generated environment with realistic reflections.ComfyUIAI Product Photography
  6. 17:062:04Background replacement with Inpaint CropThe user demonstrates a workflow using background removal and the Inpaint Crop node to swap a product's background while attempting to maintain the original item's integrity.ComfyUIAI Background Generator
  7. 19:191:08Modify hairstyles and facial featuresThe creator shows how to change a subject's hair color and style (e.g., to a blunt bob with bangs) while attempting to maintain facial consistency using Flux Kontext.ComfyUIAI Inpainting
  8. 21:030:26Edit text within an imageA demonstration of Flux Kontext's ability to change text on a 3D render from 'Welcome' to 'Pixaroma' while maintaining the original font style and perspective.ComfyUIAI Inpainting
  9. 23:191:55Remove objects using Mask Editor and InpaintingThe user demonstrates precisely removing a necklace from a portrait by painting a mask in the ComfyUI Mask Editor and using an inpainting prompt.ComfyUIAI Inpainting
  10. 25:461:20Apply LoRA models to Flux KontextThe creator shows how to use the Power Lora Loader to apply a 'Glass Prism' LoRA to a product image to transform its visual style.ComfyUIAI Style Transfer
  11. Watch “ComfyUI Tutorial Series Ep 52: Master Flux Kontext – Inpainting, Editing & Character Consistency” →

AI Image Upscaler

  1. 30:073:41Upscaling images using modelsDemonstrates upscaling a low-resolution 512x512 image using the 4X Ultra Sharp model to add clarity and detail.AI Search
  2. 36:021:32Using Preview Chooser for selective upscalingShows how to use the Image Chooser node to generate a batch of images and selectively progress only one specific image to the upscaler.AI Search
  3. 43:496:52Tiled upscaling with Ultimate SD UpscaleA detailed demo of the Ultimate SD Upscale node, showing how tiled upscaling generates significantly higher facial detail than standard upscaling.AI Search
  4. 2:432:38Generate and upscale images with Flux KontextCurrentThe creator demonstrates setting up a basic Flux Kontext workflow in ComfyUI, generating a character image, and then using a KSampler-based upscaler to increase resolution.pixaroma
  5. 9:521:53Upscale an existing image to 4K with PiDThe video demonstrates uploading a landscape photo into a ComfyUI workflow and using the PiD (Pixel Diffusion) model to upscale it to 4096 resolution in under 10 seconds.AI Search
  6. 13:200:38Compare original vs upscaled image using RG3 nodesThe user adds an 'image compare' node by RG3 to the ComfyUI canvas to show a side-by-side slider comparison of the blurry original image versus the sharp PiD upscaled result.AI Search
  7. 14:274:08Generate and upscale images using Zee Image and PiDA demonstration of a combined workflow where Zee Image Turbo generates a 1K image of a red panda which is then automatically passed into the PiD upscaler for a 4K final output.AI Search
  8. 1:491:28Simple non-AI image resizing in ComfyUIThe creator demonstrates a basic 'Upscale Image By' node that performs a standard resolution increase without AI, similar to Photoshop resizing, and uses an RG3 image comparer node to view the results.pixaroma
  9. 3:193:04Upscaling with Neural Network modelsThis clip shows how to use the 'Upscale Image (using Model)' node in ComfyUI with various PTH models like UltraSharp and 8x upscalers to sharpen and reconstruct details.pixaroma
  10. 6:233:22Tiled Diffusion upscaling with Zimage TurboThe creator walks through a complex workflow using Tiled Diffusion and the Zimage Turbo model to upscale images while managing VRAM by processing the image in smaller tiles.pixaroma
  11. 9:451:24Upscaling with Nunchaku Flux ManiaA demonstration of using a modified Flux.1 Dev model (Flux Mania) via Nunchaku nodes to perform a 2x upscale that enhances skin textures and fine details.pixaroma
  12. 11:103:10High-fidelity upscaling with SeedVR2The video shows the setup and execution of the SeedVR2 node pack, demonstrating how to select specific models and adjust resolution for sharp, consistent upscaling results.pixaroma
demobook

Show, don’t tell.

Categories

Video & AnimationImage Generation & EditingSales TechEmail Marketing

About

SubmitAboutPrivacyTermsContact

© demobook.co