demobook

ComfyUI: Fix text and faces using Crop and Stitch

ComfyUITry it →Watch full video →Matt Hallett VisualMatt Hallett Visual·

Demo summary

A demonstration of a custom 'crop image' node to isolate specific areas like signs or faces, regenerate them at native resolution, and stitch them back into the high-res image.

Step-by-step

  1. Select a mask to highlight the specific area of the image needing correction
  2. Save the masked area
  3. Input the masked image into the crop image node
  4. Enter a text prompt describing the desired change, such as 'change sign to say restaurant'
  5. Run the node to automatically scale, regenerate, and stitch the area back into the original rendering

Options

  • Use the free 'crop and stitch' version as an alternative to the custom paid node

Watch out for

  • The free 'crop and stitch' version lacks the automatic scaling feature found in the custom node

Tips

  • Use this method to fix text errors or facial details by working at the native resolution of the AI model

Highlights

“it's I think it's pretty useful. I made it for myself.”

All demos from “Local "AI Rendering" Using 3D - Explained by a Human”

  1. 3:041:18Enhance 3D clay models with Flux and ControlNetThe creator demonstrates using the Flux model in ComfyUI with a Depth ControlNet to transform a gray 3D massing model into a detailed streetcar scene while maintaining structural integrity.ComfyUIImage to Image
  2. 6:401:29Train a custom LoRA on CivitaiA step-by-step walkthrough of uploading a dataset of streetcar images to Civitai, using auto-labeling, and configuring training settings to create a custom LoRA model.CivitaiAI Image Generator
  3. 8:512:02Image-to-image enhancement with denoisingThe video shows how to use the 'denoising' strength in ComfyUI to blend a base 3D rendering with AI-generated details like autumn trees and realistic people.ComfyUIImage to Image
  4. 12:211:24Text-to-image generation with Z-Turbo and QwenDemonstration of the Z-Turbo model and Qwen text encoder to generate specific advertising text on the side of a 3D tram model within a ComfyUI workflow.ComfyUIText to Image
  5. 15:063:12Transform 3D scenes with Qwen2-VL (Qwen-Edit)The creator uses the Qwen-Edit workflow to perform complex scene modifications, such as changing weather to rain or snow, while preserving the original 3D geometry and text.ComfyUIAI Inpainting
  6. 20:221:07Fix text and faces using Crop and StitchCurrentA demonstration of a custom 'crop image' node to isolate specific areas like signs or faces, regenerate them at native resolution, and stitch them back into the high-res image.ComfyUIAI Inpainting
  7. 23:511:57Animate 3D renders with Wan 2.1The creator walks through a Wan 2.1 video generation workflow in ComfyUI, using the Painterly I2V node to control motion speed and animate a static 3D render.ComfyUIImage to Video
  8. Watch “Local "AI Rendering" Using 3D - Explained by a Human” →

AI Inpainting

  1. 16:571:43Generate composite image with Flux 2The creator demonstrates image-to-image generation by uploading two reference photos and using a text prompt to replace a logo on a coffee can with his own headshot using the Flux model.WINBUSH
  2. 20:010:28Text-to-image manipulation in ComfyUIThe video shows how to use a text prompt to attempt to rotate an object in an image within a specific node-based workflow.WINBUSH
  3. 1:111:34Configure LTX Latent Anchor Aware nodeThe video shows how to set up the LTX Latent Anchor Aware node in a ComfyUI workflow, explaining how to connect the reference image and adjust strength parameters to prevent identity drift.The AI Girlie
  4. 0:361:56Creative replacement with Flux KontextThe user demonstrates how to change a specific part of an image, such as replacing a building entrance with a glass door, using the Flux Kontext model in ComfyUI while maintaining the original scene context.Urban Decoders
  5. 5:200:53Change season to winter in architectural scenesThe demonstration shows how to use a text prompt to transform a summer architectural shot into a winter scene with snow on rooftops and trees using Flux Kontext.Urban Decoders
  6. 6:471:52Selective inpainting with crop and stitchUsing the 'ComfyUI inpaint crop and stitch' nodes, the user demonstrates masking a specific window area to insert a glowing LED digital facade.Urban Decoders
  7. 12:540:41Editing text on shop frontsThe demonstration shows how to use Flux Kontext to change specific text on a shop sign while maintaining the original font style and position.Urban Decoders
  8. 15:063:12Transform 3D scenes with Qwen2-VL (Qwen-Edit)The creator uses the Qwen-Edit workflow to perform complex scene modifications, such as changing weather to rain or snow, while preserving the original 3D geometry and text.Matt Hallett Visual
  9. 20:221:07Fix text and faces using Crop and StitchCurrentA demonstration of a custom 'crop image' node to isolate specific areas like signs or faces, regenerate them at native resolution, and stitch them back into the high-res image.Matt Hallett Visual
  10. 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.pixaroma
  11. 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.pixaroma
  12. 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.pixaroma
demobook

Show, don’t tell.

Categories

LaunchesEmail MarketingImage Generation & EditingMusic & AudioSales TechVideo & Animation

Trends

AI Fruit Video

About

SubmitAboutPrivacyTermsContact

© demobook.co