Downloads · 30 days
4
20% of all-time downloads
markod0925/yarn_flux
yarn_flux is a text-to-image model from markod0925. Use it when you need an image from a text prompt. It is set up for diffusers.
Downloads · 30 days
4
20% of all-time downloads
All-time downloads
20
Public
Parameters
6.1B
18.7 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors18.7 GB · 100%
How the weights are stored.
U85.9B · 97%
From the Hugging Face model README
Make everything as Yarn Art Syle.
Make everything as Yarn Art Syle.
!pip install -U diffusers bitsandbytes
from diffusers import AutoPipelineForText2Image, BitsAndBytesConfig
import torch
repo_id = "markod0925/yarn_flux"
bnb_4bit_compute_dtype = torch.float16
nf4_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_compute_dtype=bnb_4bit_compute_dtype,
)
pipeline = AutoPipelineForText2Image.from_pretrained(repo_id,
torch_dtype=bnb_4bit_compute_dtype
)
pipeline.enable_model_cpu_offload()
image = pipeline(
"Astronaut in a jungle, cold color palette, muted colors, detailed, 8k", num_inference_steps=28, guidance_scale=3.5, height=768
).images[0]
image

image = pipeline(
"Astronaut in a jungle, cold color palette, muted colors, detailed, 8k, yarn art style", num_inference_steps=28, guidance_scale=3.5, height=768
).images[0]
image
