import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Benevolent/HutaoV2")
prompt = "1girl, hu tao (genshin impact), hat, flower on hat,brown hair, twintails, smile, dress, long hair, off-shoulder dress, ahoge, looking at viewer, red dress, bare shoulders, grin, red eyes, flower-shaped pupils, blush, bangs, breasts, choker, collarbone, solo, nail polish, black nails, ribbon choker, bow, hair between eyes, hair ornament, sidelocks, cleavage, wrist ribbon, very long hair, teeth, cowboy shot <lora:hutao_v2:0.7>"
image = pipe(prompt).images[0]HuTaoXL
- Prompt
- 1girl, hu tao (genshin impact), hat, flower on hat,brown hair, twintails, smile, dress, long hair, off-shoulder dress, ahoge, looking at viewer, red dress, bare shoulders, grin, red eyes, flower-shaped pupils, blush, bangs, breasts, choker, collarbone, solo, nail polish, black nails, ribbon choker, bow, hair between eyes, hair ornament, sidelocks, cleavage, wrist ribbon, very long hair, teeth, cowboy shot <lora:hutao_v2:0.7>
- Negative Prompt
- nsfw, (worst quality, low quality:1.4), (lip, nose, tooth, rouge, lipstick, eyeshadow:1.4), (blush:1.2), (jpeg artifacts:1.4), (depth of field, bokeh, blurry, film grain, chromatic aberration, lens flare:1.0), (1boy, abs, muscular, rib:1.0), greyscale, monochrome, dusty sunbeams, trembling, motion lines, motion blur, emphasis lines, text, title, logo, signature, bad-artist-anime, bad_artist, bad_hands, bad_prompt, bad_prompt_version2, easynegative
Trigger words
You should use hu tao (genshin impact) to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- 3
Model tree for Benevolent/HutaoV2
Base model
stabilityai/stable-diffusion-xl-base-1.0