random / README.md
mrtuandao's picture
Model card auto-generated by SimpleTuner
46b29bb verified
---
license: other
base_model: "flux/unknown-model"
tags:
- flux
- flux-diffusers
- text-to-image
- diffusers
- simpletuner
- not-for-all-audiences
- lora
- template:sd-lora
- standard
inference: true
widget:
- text: 'unconditional (blank prompt)'
parameters:
negative_prompt: 'blurry, cropped, ugly'
output:
url: ./assets/image_0_0.png
- text: 'A Simple Pencil sketch of Marilyn Monroe, showcasing her iconic smile and glamorous hairstyle. The shading captures the softness of her features and the elegance of her famous pose, framed by a hint of her signature wardrobe.'
parameters:
negative_prompt: 'blurry, cropped, ugly'
output:
url: ./assets/image_1_0.png
---
# random
This is a standard PEFT LoRA derived from [flux/unknown-model](https://huggingface.co/flux/unknown-model).
The main validation prompt used during training was:
```
A Simple Pencil sketch of Marilyn Monroe, showcasing her iconic smile and glamorous hairstyle. The shading captures the softness of her features and the elegance of her famous pose, framed by a hint of her signature wardrobe.
```
## Validation settings
- CFG: `3.5`
- CFG Rescale: `0.0`
- Steps: `35`
- Sampler: `FlowMatchEulerDiscreteScheduler`
- Seed: `42`
- Resolution: `1024x1024`
- Skip-layer guidance:
Note: The validation settings are not necessarily the same as the [training settings](#training-settings).
You can find some example images in the following gallery:
<Gallery />
The text encoder **was not** trained.
You may reuse the base model text encoder for inference.
## Training settings
- Training epochs: 2
- Training steps: 1000
- Learning rate: 0.0001
- Learning rate schedule: polynomial
- Warmup steps: 100
- Max grad norm: 2.0
- Effective batch size: 1
- Micro-batch size: 1
- Gradient accumulation steps: 1
- Number of GPUs: 1
- Gradient checkpointing: True
- Prediction type: flow-matching (extra parameters=['shift=3', 'flux_guidance_mode=constant', 'flux_guidance_value=1.0', 'flow_matching_loss=compatible', 'flux_lora_target=all'])
- Optimizer: adamw_bf16
- Trainable parameter precision: Pure BF16
- Caption dropout probability: 10.0%
- LoRA Rank: 32
- LoRA Alpha: None
- LoRA Dropout: 0.1
- LoRA initialisation style: default
## Datasets
### pencil-sketch-image
- Repeats: 10
- Total number of images: 31
- Total number of aspect buckets: 1
- Resolution: 1.048576 megapixels
- Cropped: True
- Crop style: random
- Crop aspect: square
- Used for regularisation data: No
## Inference
```python
import torch
from diffusers import DiffusionPipeline
model_id = '/workspace/FLUX.1-dev'
adapter_id = 'mrtuandao/random'
pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
pipeline.load_lora_weights(adapter_id)
prompt = "A Simple Pencil sketch of Marilyn Monroe, showcasing her iconic smile and glamorous hairstyle. The shading captures the softness of her features and the elegance of her famous pose, framed by a hint of her signature wardrobe."
## Optional: quantise the model to save on vram.
## Note: The model was not quantised during training, so it is not necessary to quantise it during inference time.
#from optimum.quanto import quantize, freeze, qint8
#quantize(pipeline.transformer, weights=qint8)
#freeze(pipeline.transformer)
pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu') # the pipeline is already in its target precision level
image = pipeline(
prompt=prompt,
num_inference_steps=35,
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=3.5,
).images[0]
image.save("output.png", format="PNG")
```