Text-to-Image
Diffusers
flux
flux-diffusers
image-to-image
simpletuner
safe-for-work
lora
template:sd-lora
standard
Instructions to use cmyau/simpletuner-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use cmyau/simpletuner-lora with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("cmyau/simpletuner-lora") prompt = "unconditional (blank prompt)" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Commit History
-
Model card auto-generated by SimpleTuner
Verified signature8bd07c7 -
Trained for 0 epochs and 5001 steps.
Verified signatureTrained with datasets ['text-embed-cache', 'chenille-dataset-256', 'chenille-dataset-crop-256', 'chenille-dataset-512', 'chenille-dataset-crop-512', 'chenille-dataset-768', 'chenille-dataset-crop-768', 'chenille-dataset-1024', 'chenille-dataset-crop-1024', 'chenille-dataset-1440', 'chenille-dataset-crop-1440'] Learning rate 8e-05, batch size 1, and 1 gradient accumulation steps. Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False Using 'trailing' timestep spacing. Base model: black-forest-labs/FLUX.1-dev VAE: Nonebbc75a6 -
Validation images auto-generated by SimpleTuner
Verified signature24c85fe -
Model card auto-generated by SimpleTuner
Verified signaturee04a3e2 -
Trained for 0 epochs and 5000 steps.
Verified signatureTrained with datasets ['text-embed-cache', 'chenille-dataset-256', 'chenille-dataset-crop-256', 'chenille-dataset-512', 'chenille-dataset-crop-512', 'chenille-dataset-768', 'chenille-dataset-crop-768', 'chenille-dataset-1024', 'chenille-dataset-crop-1024', 'chenille-dataset-1440', 'chenille-dataset-crop-1440'] Learning rate 8e-05, batch size 1, and 1 gradient accumulation steps. Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False Using 'trailing' timestep spacing. Base model: black-forest-labs/FLUX.1-dev VAE: Noneb4e4bf7 -
Validation images auto-generated by SimpleTuner
Verified signature79a5511
-
initial commit
Verified signature24ddb61