demobook

Loading PDF prompt techniques into ComfyUI

Demo summary

The user shows how to upload a PDF containing prompt engineering techniques into the ComfyUI input folder and reference it using the Input Files node.

Step-by-step

  1. Select the downloaded PDF file from the Input Files node
  2. Navigate to the OpenAI Chat node options
  3. Input the system prompt instructions to reference the PDF techniques and output the prompt in English
  4. Drag and drop the workflow into ComfyUI
  5. Place the PDF file into the ComfyUI input folder

Options

  • Download the pre-configured workflow and PDF from Discord to skip manual setup

Watch out for

  • The PDF file must be placed in the input folder before it can be selected in the node

Tips

  • Use this method to optimize prompts for different specific flows by loading specialized system prompts or techniques
  • Instruct the system prompt to output only the prompt in English for best results

Highlights

ワークフローならドラッグするだけ。 PDFファイルはこちら入力フォルダーに入れるだけ。システムプロンプはコピーペをするだけなので簡単だと思います。

All demos from “【無料】Flux.1 Kontextのローカル生成が良い!一貫性も合成も最強クラスの性能です。

  1. 2:000:50Setting up FLUX.1 Kontext Dev in ComfyUIThe creator demonstrates how to load the 'context dev' basic template in ComfyUI and download the necessary model files directly through the manager.ComfyUIAI Image Generator
  2. 7:531:06Loading PDF prompt techniques into ComfyUICurrentThe user shows how to upload a PDF containing prompt engineering techniques into the ComfyUI input folder and reference it using the Input Files node.ComfyUIAI Image Generator
  3. 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.ComfyUIImage to Image
  4. 10:260:54Merging two characters with Kontext Dev Grouped workflowThe video shows the 'grouped' workflow in ComfyUI, where two separate character images are referenced to generate a single composite image of them hugging.ComfyUIAI Image Combiner
  5. Watch “【無料】Flux.1 Kontextのローカル生成が良い!一貫性も合成も最強クラスの性能です。” →

AI Image Generator

  1. 1:560:39Load a text-to-image workflow and download missing modelsThe user demonstrates how to load a default text-to-image template in ComfyUI and use the 'show missing models' feature to download required AI checkpoints.Kevin Stratvert
  2. 4:110:29Manage generated assets in ComfyUIThe presenter demonstrates how to access the assets panel using the 'A' shortcut to view, save, or delete previously generated images.Kevin Stratvert
  3. 15:005:45Generate image with Hermes Agent and ComfyUIThe host uses the Hermes Agent TUI to request a 1024x1024 image of a tree using the Zimage Turbo model, which the agent executes by generating and running a ComfyUI workflow.ComfyUI
  4. 6:420:59Configure Gemma 2B Text Encoder in ComfyUIThe creator shows how to load the Gemma 2B text encoder model into the ComfyUI workflow and select it from the node dropdown menu.AI Search
  5. 4:270:30Copying and replacing prompts in ComfyUIThe user demonstrates a custom node feature that allows hovering over prompt examples to copy and then replace the current prompt in the workflow with a single click.pixaroma
  6. 13:030:51Managing node colors with PixaRoma nodesThe video demonstrates UI updates for PixaRoma nodes in ComfyUI, including selecting color swatches, copying/pasting colors between nodes, and setting favorite colors.pixaroma
  7. 4:150:35Launch ComfyUI on WindowsThe creator demonstrates how to launch the portable version of ComfyUI by running the 'run_nvidia_gpu' batch file and accessing the interface via a web browser.WINBUSH
  8. 10:071:30Browse and load ComfyUI templatesThe creator demonstrates how to navigate the templates menu, filter for local models, and load a Flux 2 image generation workflow.WINBUSH
  9. 0:000:33Configuring MSR mode in LTX DirectorThe user demonstrates setting up the Director node in ComfyUI for MSR (Multiple Subject Reference) mode, including bypassing clean latent slices and enabling the MSR LoRA.RedShade
  10. 5:090:19Loading LTX Director V5 workflow templateThe video shows how to search for and load the LTX Director V5 template within ComfyUI and input prompts for character generation.RedShade
  11. 4:251:21Iterative rerolling at specific generation stagesThe video shows how to use the 'reroll' button at specific stages of the workflow to change motion or visual quality without re-generating the initial seed samples.Fox•Fur•Essence Films
  12. 9:173:04Install ComfyUI using Easy InstallThe instructor demonstrates how to download the ComfyUI Easy Install zip from GitHub, extract it, and run the BAT file to set up a portable local installation.pixaroma