Edit model card

pseudo-flex-v2

This is a full rank finetuned model derived from stabilityai/stable-diffusion-2-1.

The main validation prompt used during training was:

a cinematic scene from the film Rogue One, a woman stares off into the distance, holding a sign that reads SOON

Validation settings

  • CFG: 9.2
  • CFG Rescale: 0.7
  • Steps: 30
  • Sampler: euler
  • Seed: 420420420
  • Resolutions: 1024x1024,1152x960,896x1152

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: 4
  • Training steps: 48700
  • Learning rate: 4e-07
  • Effective batch size: 32
    • Micro-batch size: 4
    • Gradient accumulation steps: 8
  • Prediction type: v_prediction
  • Rescaled betas zero SNR: True
  • Optimizer: AdamW, stochastic bf16
  • Precision: Pure BF16
  • Xformers: Enabled

Datasets

celebrities

  • Repeats: 0
  • Total number of images: 1216
  • Total number of aspect buckets: 3
  • Resolution: 1.0 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: random

movieposters

  • Repeats: 0
  • Total number of images: 1696
  • Total number of aspect buckets: 3
  • Resolution: 1.0 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: random

normalnudes

  • Repeats: 0
  • Total number of images: 1088
  • Total number of aspect buckets: 3
  • Resolution: 1.0 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: random

propagandaposters

  • Repeats: 0
  • Total number of images: 640
  • Total number of aspect buckets: 3
  • Resolution: 1.0 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: random

guys

  • Repeats: 0
  • Total number of images: 352
  • Total number of aspect buckets: 3
  • Resolution: 1.0 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: random

pixel-art

  • Repeats: 0
  • Total number of images: 1056
  • Total number of aspect buckets: 3
  • Resolution: 1.0 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: random

signs

  • Repeats: 0
  • Total number of images: 384
  • Total number of aspect buckets: 3
  • Resolution: 1.0 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: random

moviecollection

  • Repeats: 0
  • Total number of images: 1856
  • Total number of aspect buckets: 3
  • Resolution: 1.0 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: random

bookcovers

  • Repeats: 0
  • Total number of images: 768
  • Total number of aspect buckets: 3
  • Resolution: 1.0 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: random

nijijourney

  • Repeats: 0
  • Total number of images: 640
  • Total number of aspect buckets: 3
  • Resolution: 1.0 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: random

experimental

  • Repeats: 0
  • Total number of images: 3008
  • Total number of aspect buckets: 3
  • Resolution: 1.0 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: random

ethnic

  • Repeats: 0
  • Total number of images: 3072
  • Total number of aspect buckets: 3
  • Resolution: 1.0 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: random

sports

  • Repeats: 0
  • Total number of images: 800
  • Total number of aspect buckets: 3
  • Resolution: 1.0 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: random

gay

  • Repeats: 0
  • Total number of images: 1056
  • Total number of aspect buckets: 3
  • Resolution: 1.0 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: random

architecture

  • Repeats: 0
  • Total number of images: 4320
  • Total number of aspect buckets: 3
  • Resolution: 1.0 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: random

shutterstock

  • Repeats: 0
  • Total number of images: 21056
  • Total number of aspect buckets: 3
  • Resolution: 1.0 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: random

cinemamix-1mp

  • Repeats: 0
  • Total number of images: 8992
  • Total number of aspect buckets: 3
  • Resolution: 1.0 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: random

nsfw-1024

  • Repeats: 0
  • Total number of images: 10784
  • Total number of aspect buckets: 3
  • Resolution: 1.0 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: random

anatomy

  • Repeats: 5
  • Total number of images: 16352
  • Total number of aspect buckets: 3
  • Resolution: 1.0 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: random

bg20k-1024

  • Repeats: 0
  • Total number of images: 89248
  • Total number of aspect buckets: 3
  • Resolution: 1.0 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: random

yoga

  • Repeats: 0
  • Total number of images: 3552
  • Total number of aspect buckets: 3
  • Resolution: 1.0 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: random
Downloads last month
1,891
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for bghira/pseudo-flex-v2

Finetuned
(160)
this model

Space using bghira/pseudo-flex-v2 1