metadata
license: other
base_model: stabilityai/stable-diffusion-3.5-large
tags:
- sd3
- sd3-diffusers
- text-to-image
- diffusers
- simpletuner
- not-for-all-audiences
- lora
- template:sd-lora
- lycoris
inference: true
widget:
- text: unconditional (blank prompt)
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_0_0.png
- text: a picture of tommy chong
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_1_0.png
- text: young tommy chong
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_2_0.png
- text: >-
a stoic photograph of tommy chong. he looks off into the distance,
standing up against the railing of a ship. the sky is cloudy.
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_3_0.png
- text: an elderly tommy chong as a contestant on Wheel of Fortune
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_4_0.png
- text: >-
tommy chong as a superhero in the style of studio ghibli. he wears a metal
armor suit with glowing lights and power indicators.
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_5_0.png
- text: >-
tommy chong in a casket, dead. he is dead and it is a funeral. the text
overhead says 'HE HAS NOT RISEN'.
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_6_0.png
- text: a picture of cheech marin
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_7_0.png
- text: young cheech marin
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_8_0.png
- text: >-
a stoic photograph of cheech marin. he looks off into the distance,
standing up against the railing of a ship. the sky is cloudy.
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_9_0.png
- text: an elderly cheech marin as a contestant on Wheel of Fortune
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_10_0.png
- text: >-
cheech marin as a superhero in the style of studio ghibli. he wears a
metal armor suit with glowing lights and power indicators.
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_11_0.png
- text: >-
cheech marin in a casket, dead. he is dead and it is a funeral. the text
overhead says 'HE HAS NOT RISEN'.
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_12_0.png
- text: >-
cheech marin sitting to the left of tommy chong on the set of a television
interview
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_13_0.png
- text: >-
cheech marin sitting to the right of tommy chong on the set of a
television interview
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_14_0.png
- text: >-
cheech and chong sitting together on the stoop of a new york apartment
building, 1972
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_15_0.png
- text: >-
the iconic duo cheech and chong on stage performing stand-up comedy
together in 2008
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_16_0.png
- text: A photo-realistic image of a cat
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_17_0.png
sd3-cheechandchong-regularised
This is a LyCORIS adapter derived from stabilityai/stable-diffusion-3.5-large.
The main validation prompt used during training was:
A photo-realistic image of a cat
Validation settings
- CFG:
4.0
- CFG Rescale:
0.0
- Steps:
20
- Sampler:
None
- Seed:
42
- Resolution:
1024x1024
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: 100
- Learning rate: 1e-05
- Max grad norm: 0.01
- Effective batch size: 12
- Micro-batch size: 4
- Gradient accumulation steps: 1
- Number of GPUs: 3
- Prediction type: flow-matching
- Rescaled betas zero SNR: False
- Optimizer: optimi-lion
- Precision: Pure BF16
- Quantised: Yes: int8-quanto
- Xformers: Not used
- LyCORIS Config:
{
"bypass_mode": true,
"algo": "lokr",
"multiplier": 1.0,
"full_matrix": true,
"linear_dim": 10000,
"linear_alpha": 1,
"factor": 12,
"apply_preset": {
"target_module": [
"JointTransformerBlock"
],
"module_algo_map": {
"FeedForward": {
"factor": 6
},
"JointTransformerBlock": {
"factor": 12
}
}
}
}
Datasets
cheechandchong-cropped-1024
- Repeats: 10
- Total number of images: ~24
- Total number of aspect buckets: 7
- Resolution: 1.048576 megapixels
- Cropped: False
- Crop style: None
- Crop aspect: None
- Used for regularisation data: No
Inference
import torch
from diffusers import DiffusionPipeline
from lycoris import create_lycoris_from_weights
model_id = 'stabilityai/stable-diffusion-3.5-large'
adapter_id = 'pytorch_lora_weights.safetensors' # you will have to download this manually
lora_scale = 1.0
wrapper, _ = create_lycoris_from_weights(lora_scale, adapter_id, pipeline.transformer)
wrapper.merge_to()
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=20,
generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(1641421826),
width=1024,
height=1024,
guidance_scale=4.0,
).images[0]
image.save("output.png", format="PNG")