Instructions to use paconaranjo/inah with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use paconaranjo/inah 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("paconaranjo/inah") prompt = "inah" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Download train.bat from paconaranjo/inah: direct link, hf CLI and curl.
- Browser
- Download file 1.33 kB
-
https://huggingface.co/paconaranjo/inah/resolve/main/train.bat
- Command line
-
hf download hf://paconaranjo/inah/train.bat
-
curl -L -o train.bat https://huggingface.co/paconaranjo/inah/resolve/main/train.bat
1.33 kB
| accelerate launch ^ | |
| --mixed_precision bf16 ^ | |
| --num_cpu_threads_per_process 1 ^ | |
| sd-scripts/flux_train_network.py ^ | |
| --pretrained_model_name_or_path "C:\Pinokio\api\Fluxgym\models\unet\flux1-dev.sft" ^ | |
| --clip_l "C:\Pinokio\api\Fluxgym\models\clip\clip_l.safetensors" ^ | |
| --t5xxl "C:\Pinokio\api\Fluxgym\models\clip\t5xxl_fp16.safetensors" ^ | |
| --ae "C:\Pinokio\api\Fluxgym\models\vae\ae.sft" ^ | |
| --cache_latents_to_disk ^ | |
| --save_model_as safetensors ^ | |
| --sdpa --persistent_data_loader_workers ^ | |
| --max_data_loader_n_workers 2 ^ | |
| --seed 42 ^ | |
| --gradient_checkpointing ^ | |
| --mixed_precision bf16 ^ | |
| --save_precision bf16 ^ | |
| --network_module networks.lora_flux ^ | |
| --network_dim 4 ^ | |
| --optimizer_type adamw8bit ^--sample_prompts="C:\Pinokio\api\Fluxgym\outputs\inah\sample_prompts.txt" --sample_every_n_steps="500" ^ | |
| --learning_rate 8e-4 ^ | |
| --cache_text_encoder_outputs ^ | |
| --cache_text_encoder_outputs_to_disk ^ | |
| --fp8_base ^ | |
| --highvram ^ | |
| --max_train_epochs 10 ^ | |
| --save_every_n_epochs 4 ^ | |
| --dataset_config "C:\Pinokio\api\Fluxgym\outputs\inah\dataset.toml" ^ | |
| --output_dir "C:\Pinokio\api\Fluxgym\outputs\inah" ^ | |
| --output_name inah ^ | |
| --timestep_sampling shift ^ | |
| --discrete_flow_shift 3.1582 ^ | |
| --model_prediction_type raw ^ | |
| --guidance_scale 1 ^ | |
| --loss_type l2 ^ |