sd35m-sfwbooru
This is a full rank finetune derived from stabilityai/stable-diffusion-3.5-medium.
The main validation prompt used during training was:
A photo-realistic image of a cat
Validation settings
- CFG:
4.2
- CFG Rescale:
0.0
- Steps:
30
- Sampler:
FlowMatchEulerDiscreteScheduler
- Seed:
42
- Resolution:
1024x1024
- Skip-layer guidance:
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: 0
- Training steps: 100
- Learning rate: 1.0
- Learning rate schedule: constant
- Warmup steps: 500
- Max grad norm: 0.01
- Effective batch size: 6
- Micro-batch size: 6
- Gradient accumulation steps: 1
- Number of GPUs: 1
- Gradient checkpointing: True
- Prediction type: flow-matching (extra parameters=['shift=3'])
- Optimizer: prodigy
- Trainable parameter precision: Pure BF16
- Caption dropout probability: 10.0%
Datasets
sfwbooru-crop
- Repeats: 0
- Total number of images: 363920
- Total number of aspect buckets: 1
- Resolution: 1.048576 megapixels
- Cropped: True
- Crop style: random
- Crop aspect: square
- Used for regularisation data: No
sfwbooru
- Repeats: 0
- Total number of images: 469191
- Total number of aspect buckets: 70
- Resolution: 1.048576 megapixels
- Cropped: False
- Crop style: None
- Crop aspect: None
- Used for regularisation data: No
Inference
import torch
from diffusers import DiffusionPipeline
model_id = 'bghira/sd35m-sfwbooru'
pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
prompt = "A photo-realistic image of a cat"
negative_prompt = 'blurry, cropped, ugly'
pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
image = pipeline(
prompt=prompt,
negative_prompt=negative_prompt,
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(42),
width=1024,
height=1024,
guidance_scale=4.2,
).images[0]
image.save("output.png", format="PNG")