Instructions to use moonlightbaee/retro with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use moonlightbaee/retro with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("cagliostrolab/animagine-xl-4.0", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("moonlightbaee/retro") prompt = "A young, light-skinned female anime character, positioned in the mid-right of the image, sits on a balcony overlooking a stylized Parisian cityscape at sunset. She is relaxed, leaning slightly toward the viewer. Her light pink hair is long and wavy, styled in a voluminous fashion. Large, expressive, light brown eyes look directly at the viewer. Her expression is joyful and cheerful. She wears a light pink and white dress with frills and lace details and a light pink skirt accented with snowflake patterns. She has a delicate build and is dressed in light-colored and pastel-colored clothing. Her attire also includes white, patterned socks and pink shoes with embellishments. The overall color palette is vibrant, consisting mainly of pastel pinks, light blues, and purples, with glittering effects suggesting magic or enchantment. The Eiffel Tower is visible in the background, along with buildings in a similar pastel color scheme and flowers and butterflies. A yellow cat-like character sits on the balcony railing with the young woman. The style is anime, with a focus on bright colors and exaggerated features. The light source is soft, suggesting a warm, romantic glow from a light source behind the character. The perspective is slightly angled from the viewer to the balcony, drawing attention to the character's relaxed pose and the Parisian ambiance. A decorative window frame is visible, emphasizing the balcony scene. The composition is well-balanced, showcasing the character and background details in harmonious ways." image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Welcome to the community
The community tab is the place to discuss and collaborate with the HF community!