metadata
license: creativeml-openrail-m
base_model: ptx0/pixart-900m-1024-ft-large
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- simpletuner
- full
inference: true
widget:
- text: unconditional (blank prompt)
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_0_0.png
- text: unconditional (blank prompt)
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_1_1.png
- text: unconditional (blank prompt)
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_2_2.png
pixart-900m-1024-ft
This is a full rank finetune derived from ptx0/pixart-900m-1024-ft-large.
The main validation prompt used during training was:
ethnographic photography of teddy bear at a picnic holding a sign that reads SOON
Validation settings
- CFG:
7.5
- CFG Rescale:
0.0
- Steps:
30
- Sampler:
euler
- Seed:
42
- Resolutions:
1024x1024,1344x768,916x1152
Note: The validation settings are not necessarily the same as the training settings.
You can find some example images in the following gallery:
The text encoder was not trained.
You may reuse the base model text encoder for inference.
Training settings
- Training epochs: 1
- Training steps: 33000
- Learning rate: 1e-06
- Effective batch size: 192
- Micro-batch size: 24
- Gradient accumulation steps: 1
- Number of GPUs: 8
- Prediction type: epsilon
- Rescaled betas zero SNR: False
- Optimizer: AdamW, stochastic bf16
- Precision: Pure BF16
- Xformers: Not used
Datasets
photo-concept-bucket
- Repeats: 0
- Total number of images: ~564672
- Total number of aspect buckets: 6
- Resolution: 1.0 megapixels
- Cropped: False
- Crop style: None
- Crop aspect: None
moviecollection
- Repeats: 15
- Total number of images: ~768
- Total number of aspect buckets: 11
- Resolution: 1.0 megapixels
- Cropped: True
- Crop style: random
- Crop aspect: random
experimental
- Repeats: 0
- Total number of images: ~1728
- Total number of aspect buckets: 11
- Resolution: 1.0 megapixels
- Cropped: True
- Crop style: random
- Crop aspect: random
ethnic
- Repeats: 0
- Total number of images: ~1152
- Total number of aspect buckets: 7
- Resolution: 1.0 megapixels
- Cropped: True
- Crop style: random
- Crop aspect: random
sports
- Repeats: 0
- Total number of images: ~576
- Total number of aspect buckets: 1
- Resolution: 1.0 megapixels
- Cropped: True
- Crop style: random
- Crop aspect: square
architecture
- Repeats: 0
- Total number of images: ~4224
- Total number of aspect buckets: 1
- Resolution: 1.0 megapixels
- Cropped: True
- Crop style: random
- Crop aspect: square
shutterstock
- Repeats: 0
- Total number of images: ~14016
- 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: ~7296
- 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: ~10368
- 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: ~15168
- 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: ~89088
- 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: ~2880
- Total number of aspect buckets: 3
- Resolution: 1.0 megapixels
- Cropped: True
- Crop style: random
- Crop aspect: random
photo-aesthetics
- Repeats: 0
- Total number of images: ~28608
- Total number of aspect buckets: 17
- Resolution: 1.0 megapixels
- Cropped: True
- Crop style: random
- Crop aspect: random
text-1mp
- Repeats: 125
- Total number of images: ~12864
- Total number of aspect buckets: 3
- Resolution: 1.0 megapixels
- Cropped: True
- Crop style: random
- Crop aspect: random
movieposters
- Repeats: 10
- Total number of images: ~192
- Total number of aspect buckets: 1
- Resolution: 1.0 megapixels
- Cropped: True
- Crop style: random
- Crop aspect: square
normalnudes
- Repeats: 10
- Total number of images: ~384
- Total number of aspect buckets: 8
- Resolution: 1.0 megapixels
- Cropped: True
- Crop style: random
- Crop aspect: random
pixel-art
- Repeats: 0
- Total number of images: ~384
- Total number of aspect buckets: 11
- 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: 1
- Resolution: 1.0 megapixels
- Cropped: True
- Crop style: random
- Crop aspect: square
midjourney-v6-520k-raw
- Repeats: 0
- Total number of images: ~513792
- Total number of aspect buckets: 7
- Resolution: 1.0 megapixels
- Cropped: False
- Crop style: None
- Crop aspect: None
sfwbooru
- Repeats: 0
- Total number of images: ~271488
- Total number of aspect buckets: 16
- Resolution: 1.0 megapixels
- Cropped: False
- Crop style: None
- Crop aspect: None
nijijourney-v6-520k-raw
- Repeats: 0
- Total number of images: ~516288
- Total number of aspect buckets: 5
- Resolution: 1.0 megapixels
- Cropped: False
- Crop style: None
- Crop aspect: None
dalle3
- Repeats: 0
- Total number of images: ~1119168
- Total number of aspect buckets: 1
- Resolution: 1.0 megapixels
- Cropped: False
- Crop style: None
- Crop aspect: None
Inference
import torch
from diffusers import DiffusionPipeline
model_id = 'pixart-900m-1024-ft'
prompt = 'ethnographic photography of teddy bear at a picnic holding a sign that reads SOON'
negative_prompt = 'blurry, cropped, ugly'
pipeline = DiffusionPipeline.from_pretrained(model_id)
pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
prompt = "ethnographic photography of teddy bear at a picnic holding a sign that reads SOON"
negative_prompt = "blurry, cropped, ugly"
pipeline = DiffusionPipeline.from_pretrained(model_id)
pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
image = pipeline(
prompt=prompt,
negative_prompt='blurry, cropped, ugly',
num_inference_steps=30,
generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(1641421826),
width=1152,
height=768,
guidance_scale=7.5,
guidance_rescale=0.0,
).images[0]
image.save("output.png", format="PNG")