YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

Genshin Impact Varesa Flux lora Early Usage

Installtion

pip install -U diffusers transformers torch sentencepiece peft controlnet-aux moviepy protobuf

Demo

import torch
from diffusers import FluxPipeline

pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
pipe.load_lora_weights("my_first_flux_lora_v1.safetensors")
pipe.enable_sequential_cpu_offload()

prompt = "In the style of Varesa , This digital anime-style drawing features Varesa, a pink-haired character with large, expressive purple eyes. She wears a black crop top, a short pleated skirt, and thigh-high white stockings with red accents. She has a bell collar and a star-shaped hair clip. Varesa holds a sandwich in her hands"

image = pipe(prompt,
             num_inference_steps=50,
             guidance_scale=3.5,
            ).images[0]
image.save("Varesa.png")

from IPython import display
display.Image("Varesa.png", width=512, height=512)

image/png

prompt = "In the style of Varesa , In this vibrant anime-style digital artwork, Varesa, a cute girl with long, wavy pink hair, wears a black and white outfit with a crop top, thigh-high socks, and a heart-shaped knee patch. She sits on a wooden bench in a sunny village with rustic houses and rolling hills. Her large purple eyes and horn-like hair accessories add to her enchanting appearance. The background features fluffy clouds and distant mountains."

image = pipe(prompt,
             num_inference_steps=50,
             guidance_scale=3.5,
            ).images[0]
image.save("Varesa.png")

from IPython import display
display.Image("Varesa.png", width=512, height=512)

image/png

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support