demobook

Generate image with Hermes Agent and ComfyUI

Demo summary

The 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.

Step-by-step

  1. Verify ComfyUI is running locally on port 8188
  2. Enter a natural language prompt into the Hermes Agent TUI specifying the model and dimensions
  3. Wait for the agent to load the creative comfy skill and generate the workflow
  4. Open the Windows 'Run' dialog (Start + R)
  5. Type '\\wsl$' to access the WSL network file system
  6. Navigate to the home folder, then to the ComfyUI output directory to view the generated image

Options

  • Use the 'template integrity skill' to prevent the agent from simplifying complex workflows
  • Request access to the Comfy MCP alpha by leaving a message on X or YouTube

Watch out for

  • The agent cannot reliably build workflows from scratch and often creates non-functional solutions
  • The agent tends to over-simplify complex workflows (e.g., reducing 48 nodes to 12), resulting in poor quality output
  • WSL file systems are encrypted and must be accessed as a network device rather than a standard local drive on Windows

Tips

  • Don't let the agent rebuild workflows if it detects specific text encoders like Quen, as it may break the process
  • Ensure the agent references a templates repo for the 'source of truth' rather than letting it hallucinate workflow structures
  • Sort the output folder by date to quickly find the most recently generated image

Highlights

having it just work right off the straight up skill, you will be a sad sad person.

All demos from “ComfyUI Skill in Hermes Agent Deep Dive

  1. 15:005:45Generate image with Hermes Agent and ComfyUICurrentThe 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.ComfyUIAI Image Generator
  2. 22:4831:45Automated video generation and stitching with Hermes AgentThe Hermes Agent is used to generate four separate videos of trees using LTX 2.3 in ComfyUI and then automatically stitch them together with 1-second crossfades using a tool call to FFmpeg.ComfyUIAI Movie Generator
  3. Watch “ComfyUI Skill in Hermes Agent Deep Dive” →

AI Image Generator

  1. 8:418:40Building a ComfyUI workflow from scratchA step-by-step walkthrough of adding nodes (Checkpoint, CLIP Text Encode, KSampler, VAE Decode) and connecting them to build a custom image generation pipeline.AI Search
  2. 19:571:09Generating a medieval warrior with batch processingDemonstrates generating multiple images of a medieval warrior by increasing the batch size in the Empty Latent Image node.AI Search
  3. 25:330:32Importing workflows from image metadataShows how to drag an existing AI-generated image into the ComfyUI canvas to automatically reconstruct the entire node workflow used to create it.AI Search
  4. 58:094:05Controlling character poses with ControlNetDemonstrates using the OpenPose pre-processor and ControlNet Union model to force a generated princess character into a specific pose from a reference image.AI Search
  5. 1:360:57Install custom workflows and missing nodes in ComfyUIThe video demonstrates how to drag and drop a JSON workflow file into ComfyUI and use the Manager to identify and install missing custom nodes.Sebastian Kamph
  6. 3:020:20Search and install models via Model ManagerA walkthrough of using the ComfyUI Model Manager to search for specific AI models, such as ControlNet, and install them directly.Sebastian Kamph
  7. 3:281:10Running and managing image generation queuesDemonstration of starting a workflow using the 'Run' button, setting up 'Run Instant' for continuous generation, and using 'Run on Change' to trigger generation upon prompt edits.Sebastian Kamph
  8. 4:590:55Navigating the ComfyUI workspace and UI settingsShows how to use zoom, fit view, pan modes, and toggle link visibility or themes (light/dark mode) within the ComfyUI interface.Sebastian Kamph
  9. 11:311:49Adding and connecting nodes in ComfyUIThe video demonstrates adding a 'Load Image' node via the library or right-click menu and connecting it to other nodes like 'Save Image' using spaghetti links.Sebastian Kamph
  10. 19:431:34Converting widgets to inputs in ComfyUIShows how to convert a node's internal settings (like seed) into an external input pin and connect a 'Primitive' node to control it.Sebastian Kamph
  11. 25:032:06Managing seeds and randomizationShows the difference between 'Randomize' and 'Fixed' seed settings in the KSampler to either generate new variations or reproduce the same image.Sebastian Kamph
  12. 36:450:34Saving images to specific foldersShows how to use the 'Save Image' node and file path syntax to organize output images into custom subfolders.Sebastian Kamph