import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Yntec/ProjectKawai", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Project K (Kawai)
768x768 version of Project K (Kawai) 5.0.1-250723 for the inference API. Check its licence at the original page: https://civitai.com/models/21138?modelVersionId=125063
Samples and prompts:
(Click for larger)
Top left: street, no humans, cloud, road, building, dappled sunlight, plant, blue sky, sunlight, scenery, grass, sign, day, landspace, real world location, shade, sky, city, shadow, tree, outdoors, from below, buildings
Top right: sleeveless, smile, blue eyes, bangs, cloud, hat, straw hat, cloudy sky, summer, sitting, open mouth, cup, umbrella, crossed legs, innertube, denim shorts, sun, blue sky, looking at viewer, :d, hair between eyes, sunflower, legs, sunlight, sundress, holding cup, long hair, bare shoulders, short shorts
Bottom left: 1girl, cleavage, fox ears, black hair, violet eyes, ribbon, kimono, japanese clothes, light smile, bare shoulders, detached sleeves, cleavage, collarbone, sitting, ribbon, hair ornament
Bottom right: classic anime pretty cute little girl playing poker, iconic, 1970, from the movie, Cartoon, sharp focus. acrylic art on canvas by Clay Mann and ROSSDRAWS. CHIBI
512x512 version of Project K (Kawai) v5: https://huggingface.co/Ojimi/anime-kawai-diffusion
- Downloads last month
- 43