Downloads · 30 days
13
9% of all-time downloads
je-suis-tm/kamiki_rei_lora_flux_nf4
kamiki_rei_lora_flux_nf4 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
13
9% of all-time downloads
All-time downloads
143
Public
Repo size
19.9 MB
Likes
0
Public
Click a slice to open those files.
.safetensors18.7 MB · 94%
From the Hugging Face model README
神木麗 / かみきれい / Kamiki Rei
All files are also archived in https://github.com/je-suis-tm/huggingface-archive in case this gets censored.
The QLoRA fine-tuning process of kamiki_rei_lora_flux_nf4 takes inspiration from this post (https://huggingface.co/blog/flux-qlora). The training was executed on a local computer with 1200 timesteps and the same parameters as the link mentioned above, which took around 8 hours on 8GB VRAM 4060. The peak VRAM usage was around 7.7GB. To avoid running low on VRAM, both transformers and text_encoder were quantized. The biggest challenge of training Japanese actresses is their photos used heavy filters to whiten and smoothen the skin. This practise severely distorts the training images which makes the result less convincing than Hollywood actresses. All the images generated here are using the below parameters
import torch
from diffusers import FluxPipeline, FluxTransformer2DModel
from transformers import T5EncoderModel
text_encoder_4bit = T5EncoderModel.from_pretrained(
"hf-internal-testing/flux.1-dev-nf4-pkg", subfolder="text_encoder_2",torch_dtype=torch.float16,)
transformer_4bit = FluxTransformer2DModel.from_pretrained(
"hf-internal-testing/flux.1-dev-nf4-pkg", subfolder="transformer",torch_dtype=torch.float16,)
pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.float16,
transformer=transformer_4bit,text_encoder_2=text_encoder_4bit)
pipe.load_lora_weights("je-suis-tm/kamiki_rei_lora_flux_nf4",
weight_name='pytorch_lora_weights.safetensors')
prompt="Portrait, hyper-realistic photograph, HD, 8K, high resolution, extremely detailed. Kamiki Rei with dark hair pulled back, and a gold necklace. Her outfit consists of a mint green fuzzy jacket, a pistachio V-neck blouse, and short, tight, thong-style blue capri-style shorts with glitter. On her feet, she wears high-top boots decorated with light blue sequins or beads. In one hand, she holds a shiny box, and the other is brought to her mouth, which is slightly open. The background is an underground parking lot with several cars. Photo for a professional photoshoot for a fashion magazine. Canon EOS-1D X MARK II, realistic style, HDR, HD, 4K, 8K, 32K and 64K resolution, extremely high level of detail."
image = pipe(
prompt,
height=512,
width=512,
guidance_scale=5,
num_inference_steps=20,
max_sequence_length=512,
generator=torch.Generator("cpu").manual_seed(0),
).images[0]
image.save("kamiki_rei_lora_flux_nf4.png")
You should use Kamiki Rei to trigger the image generation.
Download them in the Files & versions tab.