nodes/redhottensors-ComfyUI-Prediction
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix missing line break in README.md

Browse Source
This commit is contained in:
redhottensors
2024-05-11 17:01:03 -06:00
parent 5c1df8e3c9
commit 5d4db24c10
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+1 -1
View File
@@ -63,7 +63,7 @@ Combines an unconditioned (or negative) prediction with a desired, conditioned (
``log_tolerance``: log<sub>10</sub> convergence tolerance. Higher values improve convergence speed but will introduce artifacts.<br>
``keep_tolerance``: A multiplier greater than 1 relaxes the tolerance requirement on the final step, returning a mostly-converged result instead of using the fallback.<br>
``reuse_scale``: A multiplier greater than 0 retains a portion of the prior correction term between samples. May improve convergence speed and consistency, but may also introduce instabilities. Use with caution.<br>
``max_steps``: Maximum number of optimizer steps before giving up and using the fallback prediction.
``max_steps``: Maximum number of optimizer steps before giving up and using the fallback prediction.<br>
``precondition_gradients``: Precondition gradients during Anderson acceleration. This is strongly recommended, but may decrease result quality in specific cases where the gradients are reliably well-conditioned.
This node is extremely expensive to evaluate. It requires four full model evaluations plus two full evaluations for each optimizer step required.