phil_lora_flux_int8_rank8
This is a standard PEFT LoRA derived from black-forest-labs/FLUX.1-dev.
The main validation prompt used during training was:
A picture of Philippe
Validation settings
- CFG:
3.0 - 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:
- Prompt
- unconditional (blank prompt)
- Negative Prompt
- blurry, cropped, ugly
- Prompt
- a breathtaking anime-style portrait of Philippe, capturing his essence with vibrant colors and expressive features
- Negative Prompt
- blurry, cropped, ugly
- Prompt
- a high-quality, detailed photograph of Philippe as a sous-chef, immersed in the art of culinary creation
- Negative Prompt
- blurry, cropped, ugly
- Prompt
- a lifelike and intimate portrait of Philippe, showcasing his unique personality and charm
- Negative Prompt
- blurry, cropped, ugly
- Prompt
- a cinematic, visually stunning photo of Philippe, emphasizing his dramatic and captivating presence
- Negative Prompt
- blurry, cropped, ugly
- Prompt
- an elegant and timeless portrait of Philippe, exuding grace and sophistication
- Negative Prompt
- blurry, cropped, ugly
- Prompt
- a dynamic and adventurous photo of Philippe, captured in an exciting, action-filled moment
- Negative Prompt
- blurry, cropped, ugly
- Prompt
- a mysterious and enigmatic portrait of Philippe, shrouded in shadows and intrigue
- Negative Prompt
- blurry, cropped, ugly
- Prompt
- a vintage-style portrait of Philippe, evoking the charm and nostalgia of a bygone era
- Negative Prompt
- blurry, cropped, ugly
- Prompt
- an artistic and abstract representation of Philippe, blending creativity with visual storytelling
- Negative Prompt
- blurry, cropped, ugly
- Prompt
- a futuristic and cutting-edge portrayal of Philippe, set against a backdrop of advanced technology
- Negative Prompt
- blurry, cropped, ugly
- Prompt
- A picture of Philippe
- Negative Prompt
- blurry, cropped, ugly
The text encoder was not trained. You may reuse the base model text encoder for inference.
Training settings
- Training epochs: 227
- Training steps: 2500
- Learning rate: 0.0004
- 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: Pure BF16
- Quantised: Yes: int8-quanto
- Xformers: Not used
- LoRA Rank: 8
- LoRA Alpha: None
- LoRA Dropout: 0.1
- LoRA initialisation style: default
Datasets
dreambooth-subject
- Repeats: 0
- Total number of images: 11
- Total number of aspect buckets: 1
- Resolution: 1.048576 megapixels
- Cropped: False
- Crop style: None
- Crop aspect: None
Inference
import torch
from diffusers import DiffusionPipeline
model_id = 'black-forest-labs/FLUX.1-dev'
adapter_id = 'PhilSad/phil_lora_flux_int8_rank8'
pipeline = DiffusionPipeline.from_pretrained(model_id)
pipeline.load_lora_weights(adapter_id)
prompt = "A picture of Philippe"
pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
image = pipeline(
prompt=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=3.0,
).images[0]
image.save("output.png", format="PNG")
- Downloads last month
- 5
Model tree for PhilSad/phil_lora_flux_int8_rank8
Base model
black-forest-labs/FLUX.1-dev