metadata

license: other
base_model: stabilityai/stable-diffusion-3-medium-diffusers
tags:
  - sd3
  - sd3-diffusers
  - text-to-image
  - diffusers
  - simpletuner
  - lora
  - template:sd-lora
inference: true
widget:
  - text: unconditional (blank prompt)
    parameters:
      negative_prompt: blurry, cropped, ugly, 3d, colorful
    output:
      url: ./assets/image_0_0.png
  - text: >-
      A simple, clear line drawing of a right-angled triangle. The right angle
      is positioned at the bottom left corner. The base of the triangle is
      labeled as '4 cm' and the height is labeled as '5 cm'. The triangle is
      drawn on a plain white background.
    parameters:
      negative_prompt: blurry, cropped, ugly, 3d, colorful
    output:
      url: ./assets/image_1_0.png

SD3-medium-Geometry-Diagrams-Lora

This is a standard PEFT LoRA derived from stabilityai/stable-diffusion-3-medium-diffusers.

The main validation prompt used during training was:

A simple, clear line drawing of a right-angled triangle. The right angle is positioned at the bottom left corner. The base of the triangle is labeled as '4 cm' and the height is labeled as '5 cm'. The triangle is drawn on a plain white background.

Validation settings

CFG: 3.0
CFG Rescale: 0.0
Steps: 25
Sampler: None
Seed: 42
Resolution: 512

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

You can find some example images in the following gallery:

Prompt
unconditional (blank prompt)

Negative Prompt
blurry, cropped, ugly, 3d, colorful

Prompt
A simple, clear line drawing of a right-angled triangle. The right angle is positioned at the bottom left corner. The base of the triangle is labeled as '4 cm' and the height is labeled as '5 cm'. The triangle is drawn on a plain white background.

Negative Prompt
blurry, cropped, ugly, 3d, colorful

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

Training settings

Training epochs: 30
Training steps: 10700
Learning rate: 0.0008
Effective batch size: 1
- Micro-batch size: 1
- Gradient accumulation steps: 1
- Number of GPUs: 1
Prediction type: flow-matching
Rescaled betas zero SNR: False
Optimizer: adamw_bf16
Precision: bf16
Quantised: No
Xformers: Not used
LoRA Rank: 32
LoRA Alpha: None
LoRA Dropout: 0.1
LoRA initialisation style: default

Datasets

right-triangles

Repeats: 0
Total number of images: 348
Total number of aspect buckets: 1
Resolution: 512 px
Cropped: True
Crop style: center
Crop aspect: square

Inference

import torch
from diffusers import DiffusionPipeline

model_id = 'stabilityai/stable-diffusion-3-medium-diffusers'
adapter_id = 'Mujeeb603/SD3-medium-Geometry-Diagrams-Lora'
pipeline = DiffusionPipeline.from_pretrained(model_id)
pipeline.load_lora_weights(adapter_id)

prompt = "A simple, clear line drawing of a right-angled triangle. The right angle is positioned at the bottom left corner. The base of the triangle is labeled as '4 cm' and the height is labeled as '5 cm'. The triangle is drawn on a plain white background."
negative_prompt = 'blurry, cropped, ugly, 3d, colorful'
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=25,
    generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(1641421826),
    width=512,
    height=512,
    guidance_scale=3.0,
).images[0]
image.save("output.png", format="PNG")