demobook

ComfyUI: Enhance 3D clay models with Flux and ControlNet

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

Demo summary

The 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.

Step-by-step

  1. Set the denoising strength to 100% to allow the prompt to generate the full image
  2. Enable the Depth ControlNet node
  3. Load the specific LoRA for your subject (e.g., TTC streetcar)
  4. Adjust the ControlNet strength to 45%
  5. Run the generation to produce the depth map and final image

Options

  • Use Control+B to toggle specific nodes on and off

Watch out for

  • Setting the ControlNet strength to 100% makes the generation too rigid and prevents the model from interpreting or adding background data like buildings

Tips

  • Use a lower ControlNet strength (around 45%) to allow the model flexibility to fill out the scene while maintaining the object's structure
  • Use a depth map to hold the location, size, and structure of the original 3D massing model

Highlights

“it looks exactly like our street car”

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

  1. 3:041:18Enhance 3D clay models with Flux and ControlNetCurrentThe 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 StitchA 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” →

Image to Image

  1. 33:282:46Image-to-image transformation with Z-ImageThe user demonstrates how to modify a ComfyUI workflow to perform image-to-image tasks, converting a 3D animation into a realistic photo using Z-Image Turbo.AI Search
  2. 1:27:395:06Image-to-Image Workflow with Denoise ControlDemonstration of converting a text-to-image workflow into an image-to-image setup using VAE Encode and adjusting the denoise parameter to control variation.pixaroma
  3. 3:041:18Enhance 3D clay models with Flux and ControlNetCurrentThe 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.Matt Hallett Visual
  4. 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.Matt Hallett Visual
  5. 32:382:30Image-to-Image generation using DenoiseDemonstrates how the Denoise slider in the KSampler affects the transformation of a source image (cat) into a new subject (dog) based on a prompt.Sebastian Kamph
  6. 2:450:14Analyzing reference images for Ghost Mask modeThe video shows the process of using the 'Analyze' button to generate a short description of a subject for the Ghost Mask reference mode.RedShade
  7. 28:561:50Image-to-Image Workflow in ComfyUIThe demo shows an image-to-image setup using a 'Load Image' node and a VAE Encode node to use an existing image as a structural guide for the K Sampler.Joey /// VP Land
  8. 9:050:49Image-to-image generation with FLUX.1 KontextDemonstration of uploading an image and using a natural language prompt to transform a character's appearance while maintaining consistency using FLUX.1 Kontext.AI様の下僕
  9. 9:314:03Image-to-image denoising with FluxThe user demonstrates how Flux handles image-to-image tasks by adjusting the denoise strength from 0.4 to 1.0 to show how it differs from Stable Diffusion.Artificial Images
  10. 41:391:29Image-to-image generation with denoisingDemonstrates the image-to-image process by loading an existing photo and adjusting the denoising strength to create variations.AI Search
  11. 4:040:41Upload character reference imageThe user shows how to upload a reference image for character replacement or stylization within the ComfyUI workflow.MDMZ
demobook

Show, don’t tell.

Categories

LaunchesEmail MarketingImage Generation & EditingMusic & AudioSales TechVideo & Animation

Trends

AI Fruit Video

About

SubmitAboutPrivacyTermsContact

© demobook.co