comfyui-performance
Skill4 starsChanged 44 days agoMITView on GitHub
Use for ComfyUI inference performance, benchmark design, kernel behavior, VRAM/RAM use, caching, loading time, throughput, latency, or regressions involving ComfyUI core, comfy-kitchen, or benchmark tooling.
In this repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- comfyui-api-and-sdkSkill
- comfyui-core-runtimeSkill
- comfyui-custom-node-backendSkill
- comfyui-developmentSkill
- comfyui-frontend-extensionSkill
- comfyui-packaging-and-registrySkill
- comfyui-self-maintenanceSkill
- comfyui-subgraphsSkill
- comfyui-testing-and-qaSkill
- comfyui-upstream-developmentSkill
- comfyui-workflowsSkill
- comfyui-workflow-validationSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 41
Before claiming a performance improvement:
- Distinctive: line 47
verify output correctness did not regress.
- Distinctive: line 48
do not claim a speedup from code inspection alone.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
ComfyUI Performance
Performance claims require measurements on a defined environment.
Sources
Use target/current:
Comfy-Org/ComfyUI;Comfy-Org/comfyui-benchmark;Comfy-Org/comfy-kitchen;Comfy-Org/comfy-model-toolsfor current model packaging or conversion behavior when relevant;Comfy-Org/comfy-quantsfor current offline quantization formats and export behavior when relevant;- relevant profiling/tests and dependency versions.
Procedure
- Record hardware, OS, driver/runtime, Python, PyTorch, ComfyUI commit, model, precision, workflow, and warm/cold state as relevant.
- Establish a baseline before changing code.
- Change one performance variable at a time where possible.
- Measure repeated runs and report variance, not a single flattering result.
- Separate prompt/setup/load time from steady-state execution when meaningful.
- Track memory use alongside speed if an optimization trades one for the other.
- Validate output correctness after optimization.
- For model conversion or quantization work, verify that the target ComfyUI loader actually supports the produced artifact before making compatibility claims.
Do not
- claim a speedup from code inspection alone;
- compare different workflows/models/hardware as if they were equivalent;
- hide OOMs, fallback paths, or reduced-quality settings in benchmark conclusions.
Acceptance gate
Before claiming a performance improvement:
- record the test environment and target commit;
- record a baseline before the change;
- repeat the after measurement under equivalent conditions;
- report variance and relevant memory use;
- verify output correctness did not regress;
- do not claim a speedup from code inspection alone.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

