import torch
from diffusers import DiffusionPipeline
from diffusers.utils import load_image
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("xiaolxl/HXHY-DollKontextLoRA", dtype=torch.bfloat16, device_map="cuda")
prompt = "Turn this cat into a dog"
input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png")
image = pipe(image=input_image, prompt=prompt).images[0]对比图（Comparison chart）：
幻象绘影万物玩偶-DollKontextLoRA。用于各类图片转换成玩偶形态，此模型具有很强的泛化能力，适用于物品/人物/动物/建筑等。
触发词：Convert to hxhy_doll style
权重：建议值1.0。
通用工作流：https://civitai.com/models/1733176/fluxkontextdev-lora-general-workflow
=======
幻象绘影万物玩偶-DollKontextLoRA. Used for converting various types of images into doll forms, this model has strong generalization capabilities and is suitable for objects/characters/animals/buildings, etc.
Trigger word: Convert to hxhy_doll style
Weight: Suggested value 1.0.
General workflow: https://civitai.com/models/1733176/fluxkontextdev-lora-general-workflow
Automatic size general workflow: https://civitai.com/models/1733187/fluxkontextdev-lora-general-workflow-auto-size-fluxkontextdev-lora
- Downloads last month
- 8