Original - Creator Incentive Program

Detailed Background

2x15-alpha-e40

Last Update：2024-05-19

Remix

#Anime

#Tools

#backround

#detail

This background LoRA for (AAA)Autism v3 is intended to add detailed backgrounds with an aesthetic to my preference.

Useful tags: detailed background, simple background, gradient background, {COLOR} background

Recommended tags: score_9, score_8, score_7

This is my first time using the Civitai Trainer. The detail is nowhere close to my satisfaction yet but it seems to have captured the aesthetic of the dataset.

⚠️ It does not work as intended with Pony v6 XL. Will try retraining with clip skip 2 to hopefully improve compatibility.

Quick Translation

Comment 0

myononon

179

207

Create (388.9K)

Favorite (270)

Download (2.0K)

Model Details

Type

LORA

Rating

4.7

Publish Time

2024-05-17

Base Model

Pony

Trigger Words

Model Source: civitai

Version Introduction

This is my first test. The training data was quite small, only 2 versions of 15 images, and only anime and furry was used so I don't know how well it will work for other uses.

Training hyperparameters:

{
  "unetLR": 0.0005,
  "clipSkip": 1,
  "loraType": "lora",
  "keepTokens": 0,
  "networkDim": 32,
  "numRepeats": 2,
  "resolution": 1024,
  "lrScheduler": "cosine_with_restarts",
  "minSnrGamma": 5,
  "noiseOffset": 0.1,
  "targetSteps": 600,
  "enableBucket": true,
  "networkAlpha": 16,
  "optimizerType": "AdamW8Bit",
  "textEncoderLR": 0.00005,
  "maxTrainEpochs": 40,
  "shuffleCaption": true,
  "trainBatchSize": 4,
  "flipAugmentation": false,
  "lrSchedulerNumCycles": 3
}

License Scope

Creative License Scope

Online Image Generation

Merge

Allow Downloads

Commercial License Scope

Sale or Commercial Use of Generated Images

Resale of Models or Their Sale After Merging