Model Card for Model ID
ํ๊ตญ์ด ์ ์ฉ ๊ฐ๋ฅ์ฑ ํ ์คํธ์ฉ (์๋ ๋ชจ๋ธ์ ๋นํด์ ์ด๋ฏธ์ง ์์ฑ ์ฑ๋ฅ์ด ๋ฎ์)
Model Details
ํ๊ตญ์ด ์ ์ฉ ๋ฐฉ๋ฒ
- black-forest-labs/FLUX.1-dev๋ฅผ ๊ธฐ๋ฐ์ผ๋ก ์ฌ์ฉ
- Bingsu/clip-vit-large-patch14-ko๋ฅผ ์ ์ฉ
- T5 Encoder์ ํ๊ตญ์ด vocab ํ์ฅ์ ์ ์ฉ + fine-tuning (์ฝ๋ฉ ์ฟผํ ์ด์๋ก ์ธํด์, 1 X A100์ 2์๊ฐ ํ์ต)
example
import torch
from diffusers import FluxPipeline
pipe = FluxPipeline.from_pretrained("jaeyong2/FLUX.1-dev-ko", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload() #save some VRAM by offloading the model to CPU. Remove this if you have enough GPU power
prompt = "ํ๋ ์๋ฅผ ๋ฌ๋ฆฌ๋ ๊ณ ์์ด'"
image = pipe(
prompt,
height=1024,
width=1024,
guidance_scale=3.5,
num_inference_steps=50,
max_sequence_length=512,
generator=torch.Generator("cpu").manual_seed(0)
).images[0]
- Downloads last month
- 22
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for jaeyong2/FLUX.1-dev-ko-Preview
Base model
black-forest-labs/FLUX.1-dev