Downloads · 30 days
17
15% of all-time downloads
je-suis-tm/pachu_torres_style_lora_flux
pachu_torres_style_lora_flux is a text-to-image model from je-suis-tm. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as mit.
Downloads · 30 days
17
15% of all-time downloads
All-time downloads
115
Public
Repo size
28.7 MB
Likes
1
Public
Click a slice to open those files.
.png19.3 MB · 67%
From the Hugging Face model README
All files are also archived in https://github.com/je-suis-tm/huggingface-archive in case this gets censored.
This a non-quantized version of https://huggingface.co/je-suis-tm/pachu_torres_style_lora_flux_nf4 with fewer female body distortions. Both are trained on the same dataset. The training is based on https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/test_dreambooth_lora_flux.py. The training took 1 hour on A100 80GB with max VRAM consumption at 33GB. The inference consumes 35GB of VRAM.
export MODEL_NAME="black-forest-labs/FLUX.1-dev"
export INSTANCE_DIR="/pvol/pachu_torres_style"
export OUTPUT_DIR="/pvol/pachu_torres_style_lora_flux"
accelerate config default
accelerate launch train_dreambooth_lora_flux1.py \
--pretrained_model_name_or_path=$MODEL_NAME \
--mixed_precision="bf16" \
--dataset_name=$INSTANCE_DIR \
--output_dir=$OUTPUT_DIR \
--gradient_checkpointing \
--instance_prompt="Pachu Torres style" \
--caption_column="text" \
--resolution=512 \
--center_crop \
--train_batch_size=1 \
--guidance_scale=1 \
--use_8bit_adam \
--checkpointing_steps=100 \
--gradient_accumulation_steps=4 \
--optimizer="adamW" \
--learning_rate=1e-4 \
--lr_scheduler="constant" \
--lr_warmup_steps=100 \
--max_train_steps=1500 \
--rank=4 \
--seed="0"
import torch
from diffusers import FluxPipeline
device = "cuda:0"
pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
pipe.load_lora_weights("je-suis-tm/pachu_torres_style_lora_flux",
weight_name='pytorch_lora_weights.safetensors')
prompt = "Pachu Torres style, A woman washes her car with a yellow sponge on a gray gravel driveway, framed by lush greenery. The woman is viewed from her rear side. She's naked with her long dark hair flowing down her back. She has soap water dripping down her ass and thighs. A vibrant hedge wall and trees form a scenic backdrop. The scene evokes a sense of peaceful solitude and intimacy, capturing a quiet moment of relaxation amidst a beautiful natural setting."
image = pipe(
prompt=prompt,
generator=torch.Generator(device=device).manual_seed(42),
num_inference_steps=50, # 28 is a good trade-off
guidance_scale=4,
height=1024,
width=1024,
).images[0]
image.save("pachu_torres_style.png")
You should use Pachu Torres Style to trigger the image generation.
Download them in the Files & versions tab.