Text-to-Image
Diffusers
stable-diffusion
stable-diffusion-diffusers
simpletuner
lora
template:sd-lora
Instructions to use ericac/flux-lora-training with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ericac/flux-lora-training 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("ericac/flux-lora-training") 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 signatureae80769 -
Trained for 24 epochs and 600 steps.
Verified signatureTrained with datasets ['text-embeds', 'default_dataset'] Learning rate 0.0001, 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: None8feb6eb -
Validation images auto-generated by SimpleTuner
Verified signature85f8041 -
Model card auto-generated by SimpleTuner
Verified signature1b4d20e -
Trained for 16 epochs and 400 steps.
Verified signatureTrained with datasets ['text-embeds', 'default_dataset'] Learning rate 0.0001, 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: Nonec222f54 -
Validation images auto-generated by SimpleTuner
Verified signaturef22fee9 -
Model card auto-generated by SimpleTuner
Verified signatureff38c26 -
Trained for 8 epochs and 200 steps.
Verified signatureTrained with datasets ['text-embeds', 'default_dataset'] Learning rate 0.0001, 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: None13d81e1 -
Validation images auto-generated by SimpleTuner
Verified signature0568032 -
initial commit
Verified signaturef0c9507