🚀 ProteusV0.2
ProteusV0.2是一款强大的文本到图像生成模型,它在OpenDalleV1.1的基础上进行了显著改进,能更好地理解提示词,在多种风格的图像生成上表现出色,尤其在超现实主义、动漫和卡通风格方面。
🚀 快速开始
模型特点
ProteusV0.2与RealCartoonXL合并,仅以0.5%的权重,就解决了无法理解与动漫或卡通风格相关标签的问题。与版本0.1相比,版本0.2有了细微但显著的改进,在提示理解上超越了MJ6,同时也接近其风格表现能力。
模型优势
Proteus是对OpenDalleV1.1的复杂增强,利用其核心功能来提供更优的结果。主要改进领域包括对提示的更高响应性和增强的创作能力。为实现这一点,它使用了约220,000张来自免版权库存图像(包含一些动漫)的GPTV字幕图像进行微调,然后进行了归一化处理。此外,还通过精心挑选的10,000对高质量AI生成图像对,采用了直接偏好优化(DPO)方法。
模型效果
为追求最佳性能,大量的低秩适应(LORA)模型被独立训练,然后通过动态应用方法有选择地整合到主模型中。这些技术在学习阶段针对模型的特定部分,同时避免干扰其他区域。因此,Proteus在描绘复杂的面部特征和逼真的皮肤纹理方面有显著改进,同时在各种美学领域,特别是超现实主义、动漫和卡通风格可视化方面保持了出色的能力。
✨ 主要特性
- 风格融合:与RealCartoonXL合并,解决动漫和卡通风格标签理解问题。
- 提示理解增强:超越MJ6的提示理解能力。
- 多风格适配:在超现实主义、动漫和卡通风格等多种美学领域表现出色。
- 细节优化:在描绘复杂面部特征和皮肤纹理方面有显著改进。
📦 安装指南
使用以下设置以获得ProteusV0.2的最佳效果:
- CFG Scale:使用8到7的CFG比例。
- Steps:20到60步以获得更多细节,20步以获得更快结果。
- Sampler:DPM++ 2M SDE
- Scheduler:Karras
- Resolution:1280x1280或1024x1024
此外,建议在提示词中使用以下关键词来提升效果:最佳质量、高清、~*~美学~*~
。
如果在构思提示词方面遇到困难,可以使用这个我整理的GPT来帮助优化提示词:点击进入
💻 使用示例
基础用法
import torch
from diffusers import (
StableDiffusionXLPipeline,
KDPM2AncestralDiscreteScheduler,
AutoencoderKL
)
vae = AutoencoderKL.from_pretrained(
"madebyollin/sdxl-vae-fp16-fix",
torch_dtype=torch.float16
)
pipe = StableDiffusionXLPipeline.from_pretrained(
"dataautogpt3/ProteusV0.2",
vae=vae,
torch_dtype=torch.float16
)
pipe.scheduler = KDPM2AncestralDiscreteScheduler.from_config(pipe.scheduler.config)
pipe.to('cuda')
prompt = "black fluffy gorgeous dangerous cat animal creature, large orange eyes, big fluffy ears, piercing gaze, full moon, dark ambiance, best quality, extremely detailed"
negative_prompt = "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image"
image = pipe(
prompt,
negative_prompt=negative_prompt,
width=1024,
height=1024,
guidance_scale=7.5,
num_inference_steps=50
).images[0]
📄 许可证
本项目采用GPL-3.0许可证。
支持作者
如果您觉得这个项目有帮助,请通过以下方式支持作者:
示例展示
| 输入提示词 | 输出图片链接 |
| ---- | ---- |
| black fluffy gorgeous dangerous cat animal creature, large orange eyes, big fluffy ears, piercing gaze, full moon, dark ambiance, best quality, extremely detailed | [ComfyUI_03087_.png](ComfyUI_03087_.png) |
| (impressionistic realism by csybgh), a 50 something male, working in banking, very short dyed dark curly balding hair, Afro-Asiatic ancestry, talks a lot but listens poorly, stuck in the past, wearing a suit, he has a certain charm, bronze skintone, sitting in a bar at night, he is smoking and feeling cool, drunk on plum wine, masterpiece, 8k, hyper detailed, smokey ambiance, perfect hands AND fingers | [GEN8-iTXcAA-okN.jpeg](GEN8-iTXcAA-okN.jpeg) |
| high quality pixel art, a pixel art silhouette of an anime space-themed girl in a space-punk steampunk style, lying in her bed by the window of a spaceship, smoking, with a rustic feel. The image should embody epic portraiture and double exposure, featuring an isolated landscape visible through the window. The colors should primarily be dynamic and action-packed, with a strong use of negative space. The entire artwork should be in pixel art style, emphasizing the characters shape and set against a white background. Silhouette | [ComfyUI_03060_.png](ComfyUI_03060_.png) |
| The image features an older man, a long white beard and mustache, He has a stern expression, giving the impression of a wise and experienced individual. The mans beard and mustache are prominent, adding to his distinguished appearance. The close-up shot of the mans face emphasizes his facial features and the intensity of his gaze. | [ComfyUI_03017_.png](ComfyUI_03017_.png) |
| Super Closeup Portrait, action shot, Profoundly dark whitish meadow, glass flowers, Stains, space grunge style, Jeanne d'Arc wearing White Olive green used styled Cotton frock, Wielding thin silver sword, Sci-fi vibe, dirty, noisy, Vintage monk style, very detailed, hd | [ComfyUI_03045.png](ComfyUI_03045.png) |
| cinematic film still of Kodak Motion Picture Film: (Sharp Detailed Image) An Oscar winning movie for Best Cinematography a woman in a kimono standing on a subway train in Japan Kodak Motion Picture Film Style, shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy | [3.png](3.png) |
| in the style of artgerm, comic style,3D model, mythical seascape, negative space, space quixotic dreams, temporal hallucination, psychedelic, mystical, intricate details, very bright neon colors, (vantablack background:1.5), pointillism, pareidolia, melting, symbolism, very high contrast, chiaroscuro | [ComfyUI_03061_.png](ComfyUI_03061_.png) |
| 1980s anime portrait of a character glitching. His face is separated from his body by heavy static. His face is deformed by pain. Dream-like, analog horror, glitch, terrifying | [ComfyUI_03092_.png](ComfyUI_03092_.png) |
| (("Proteus"):text_logo:1) | [ComfyUI_03297_.png](ComfyUI_03297_.png) |
| dan seagrave, dante, Abandon All Hope, Ye Who Enter Here, hell religious art purgatory zdzislaw Beksinski, abyss inferno, lost, wanderer | [ComfyUI_03483_.png](ComfyUI_03483_.png) |