AI GitHub
ComfyUI Examples for inspecting working graphs
Study example workflows that show how ComfyUI nodes and models fit together.
Key Takeaways
- The repository groups workflow examples by generation or editing task.
- Open an example matching the type of edit or generation you need.
- Pick a small graph and trace the model loader, conditioning and output nodes.
- Examples can reference particular weights, custom nodes or versions.
How it works
The repository groups workflow examples by generation or editing task. Many examples can be opened from workflow assets to examine the graph rather than infer settings from the rendered image.
What you need
Open an example matching the type of edit or generation you need. Read the graph's asset references before expecting it to run in a different environment.
What to try first
Pick a small graph and trace the model loader, conditioning and output nodes. Reproduce the result before substituting a checkpoint or node.
Write down the loaded models before running a downloaded graph. A missing checkpoint or an unreviewed custom node should be apparent before execution.
Where to look for failures
Examples can reference particular weights, custom nodes or versions. Verify the dependencies and terms of each artifact before installing it.
Related Franklin pages
Start with a small workflow that can be rerun. Keep the seed, mask, model revision and graph together so the visual output can be compared after an edit.
- Build reusable generation graphs around models, samplers and conditioning inputs. ComfyUI for node-based image generation
- Generate and revise images through a canvas and reusable workflows. InvokeAI for image generation and canvas editing
Franklin’s image tests give you examples of outputs to compare across visual models. Franklin’s image tests
Project documentation
Try it for your workflow
Explore the project’s documentation for setup and usage, or save this page to a collection for later.
Read the project documentation ↗