import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Yntec/Isabelia", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Isabelia
No-ema version of this model with the 840K VAE baked in. Samples and prompts (all use seed 9119):
1 girl, starry sky, close-up, anime, long hair, astronaut helmet
sailor_jupiter, night sky background. anime || masterpiece, 8k, high resolution, shallow depth of field, sharp focus
soothing tones, muted colors, high contrast, (hyperrealism, soft light, sharp),1 girl, adult german woman, freckles, black eyes, ginger quiff hair, ombre, Style-GravityMagic, focus on character, portrait, looking at viewer, solo, half shot, detailed background, piratepunkai, pirate theme:1.1), cursed sailor, privateer sailor uniform, pirate hat, dark expression, treasure map, coastal pirate town, pier, docks, camp, palm trees, peaceful, pirate tents, pirate ship on shore, sunrise, dark fantasy atmosphere,
superhero suit, realistic, cute 1girl, black hair, bodysuit, clenched hands, brown eyes, full body, gradient, gradient background, grey background, lips, medium breasts, realistic, short hair, solo, standing, superhero, yellow bodysuit
Original page:
https://civitai.com/models/189416?modelVersionId=212741 (Isabelia)
Direct link to download full version (only needed if you're going to merge the model with another one): https://huggingface.co/Yntec/BelleOfTheBall/resolve/main/isabelia_v10.safetensors
- Downloads last month
- 23