ComfyUI-EvalSampler

ComfyUI node for running evaluation after collecting latents with the EvalSampler, comparing against baseline BF16 latents. (Description by CC)

By BobJohnson24·Created 3 months ago·Updated 2 months ago· 2

BobJohnson24/ComfyUI-EvalSampler

Nodes2

On cloudLocal install

Categorysampling, model/sampling/custom

Stars2

Updated2 months ago

Nodes (2)

Eval Sampler (Advanced)

sampling

EvalSamplerAdvanced

model/sampling/custom

Readme

Run the evaluation after collecting your latents with the EvalSampler via:

python MeasureResults.py --eval-dir /Comfy/output/eval_latents --stratify-std

It expects the baseline latents to be in a sub-folder called "BF16". It then compares against every other subfolder. Results will be printed in terminal, and saved as various formats.