小鹏 G6 - XPeng G6
(CivitAI)
Model description
基于 90 张小鹏 XPeng G6 外观图片,以 720x720 分辨率训练的 LoRA。
触发词(trigger words)为:XPeng G6, a car。权重(weights)推荐 0.6-1.0,如果泛化不佳可适当降低权重,但低于 0.6 将使造成出现比较明显的瑕疵。
训练图片主要基于“熔云橙”和“新月银”两种颜色,也使用了其他几种颜色的图片,但由于数量不如前两种颜色,出图是颜色可能会不太准确。特别是“星雨青”和“星阙灰”。具体颜色对应的 trigger words 如下:
熔云橙:XPeng G6, an orange car
新月银:XPeng G6, a silver car
星云白:XPeng G6, a white car
光子蓝:XPeng G6, a blue car
星阙灰:XPeng G6, a gray car
星雨青:XPeng G6, a green car
Tips:
如果要生成 1920x1080 图片,可以 960x540 生成图片,再使用“高清修复(Hires. fix)”进行 2 倍放大。
Trigger words
You should use XPeng G6
to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('runwayml/stable-diffusion-v1-5', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('lordjia/xiao-peng-g6-xpeng-g6', weight_name='xpeng_v1.2.safetensors')
image = pipeline('masterpiece, XPeng G6, a car, sci-fi, flickering halogen lamps, muted dark colors, high dynamic range, sultry, smudge, complex details, photorealistic, masterpiece, hyperrealism, analog style, 8K UHD, RAW, octan render, concept art, professionally color graded, muted LUT, HR Giger, Hans Ruedi Giger, by Aaron Horkey and Jeremy Mann ').images[0]
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers