Auto-summarize: Fluxgym AI Training.md
This commit is contained in:
+15
-1
@@ -1,3 +1,17 @@
|
|||||||
|
---
|
||||||
|
created: '2026-04-05T05:40:04+00:00'
|
||||||
|
id: 85578143-5ecf-465f-a8a9-3d25e57e2c7f
|
||||||
|
links: []
|
||||||
|
modified: '2026-04-05T05:40:04+00:00'
|
||||||
|
summary: This note outlines the configuration parameters for training a Flux model
|
||||||
|
image generation pipeline, specifying essential requirements like repeating input
|
||||||
|
images 5 times, resizing to 1024 for high quality, and targeting 20-30 images, along
|
||||||
|
with detailed advanced settings such as learning rate, LoRA rank, noise parameters,
|
||||||
|
and batch size.
|
||||||
|
tags: []
|
||||||
|
title: Fluxgym AI Training
|
||||||
|
---
|
||||||
|
|
||||||
Suggested
|
Suggested
|
||||||
Repeat Train Images 5
|
Repeat Train Images 5
|
||||||
Resize to 1024 for HQ images
|
Resize to 1024 for HQ images
|
||||||
@@ -12,4 +26,4 @@ minimum snr gamma: 5
|
|||||||
multires noise discount: 0.3
|
multires noise discount: 0.3
|
||||||
multires noise iteration: 6
|
multires noise iteration: 6
|
||||||
noise offset: 0.1
|
noise offset: 0.1
|
||||||
train batch size: 2-4
|
train batch size: 2-4
|
||||||
Reference in New Issue
Block a user