README.md

metadata

license: creativeml-openrail-m
base_model: ptx0/terminus-xl-velocity-v1
tags:
  - stable-diffusion
  - stable-diffusion-diffusers
  - text-to-image
  - diffusers
  - full
inference: true

terminus-xl-velocity-v2

This is a full rank finetuned model derived from ptx0/terminus-xl-velocity-v1.

The main validation prompt used during training was:

a cute anime character named toast

Validation settings

• CFG: 7.5
• CFG Rescale: 0.7
• Steps: 30
• Sampler: euler
• Seed: 420420420
• Resolutions: 1024x1024,1280x768,832x1216

Note: The validation settings are not necessarily the same as the training settings.

The text encoder was not trained. You may reuse the base model text encoder for inference.

Training settings

• Training epochs: 0
• Training steps: 4200
• Learning rate: 4e-07
• Effective batch size: 8
  • Micro-batch size: 8
  • Gradient accumulation steps: 1
• Prediction type: v_prediction
• Rescaled betas zero SNR: True
• Optimizer: AdamW, stochastic bf16
• Precision: Pure BF16
• Xformers: Enabled

Datasets

mj-60

• Repeats: 0
• Total number of images: 12097
• Total number of aspect buckets: 1
• Resolution: 1.0 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None

celebrities

• Repeats: 0
• Total number of images: 1160
• Total number of aspect buckets: 20
• Resolution: 1.0 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None

experimental

• Repeats: 0
• Total number of images: 2970
• Total number of aspect buckets: 17
• Resolution: 1.0 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None

ethnic

• Repeats: 0
• Total number of images: 3009
• Total number of aspect buckets: 17
• Resolution: 1.0 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None

sports

• Repeats: 0
• Total number of images: 736
• Total number of aspect buckets: 10
• Resolution: 1.0 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None

gay

• Repeats: 0
• Total number of images: 1024
• Total number of aspect buckets: 11
• Resolution: 1.0 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None

architecture

• Repeats: 0
• Total number of images: 4258
• Total number of aspect buckets: 17
• Resolution: 1.0 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None

shutterstock

• Repeats: 0
• Total number of images: 20947
• Total number of aspect buckets: 32
• Resolution: 1.0 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None

cinemamix-1mp

• Repeats: 0
• Total number of images: 9017
• Total number of aspect buckets: 6
• Resolution: 1.0 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None

nsfw-1024

• Repeats: 0
• Total number of images: 10777
• Total number of aspect buckets: 4
• Resolution: 1.0 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None

anatomy

• Repeats: 5
• Total number of images: 16329
• Total number of aspect buckets: 21
• Resolution: 1.0 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None

bg20k-1024

• Repeats: 0
• Total number of images: 89160
• Total number of aspect buckets: 42
• Resolution: 1.0 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None

yoga

• Repeats: 0
• Total number of images: 3531
• Total number of aspect buckets: 14
• Resolution: 1.0 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None

photo-aesthetics

• Repeats: 0
• Total number of images: 33031
• Total number of aspect buckets: 24
• Resolution: 1.0 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None

text-1mp

• Repeats: 5
• Total number of images: 13118
• Total number of aspect buckets: 21
• Resolution: 1.0 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None

photo-concept-bucket

• Repeats: 0
• Total number of images: 567426
• Total number of aspect buckets: 37
• Resolution: 1.0 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None