Dreamlike Photoreal 2.0大模型

最新推荐文章于 2025-02-25 17:11:51 发布

caridle

最新推荐文章于 2025-02-25 17:11:51 发布

阅读量1.1k

点赞数

文章标签： qt 算法

本文链接：https://blog.csdn.net/caridle/article/details/130027157

版权

DreamlikePhotoreal2.0是一个基于StableDiffusion1.5的逼真模型，适用于768x768等分辨率的图像处理，也可处理更高分辨率。用户可以从dreamlike.art获取并使用该模型，它可以通过StableDiffusionPipeline在GPU上运行，例如用于创建具有特定场景描述的图片。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

Dreamlike Photoreal 2.0 is a photorealistic model based on Stable Diffusion 1.5, made by dreamlike.art.

该模型是在768x768像素的图像上进行训练的，因此请使用768x768像素、640x896像素、896x640像素等分辨率。它也可以很好地处理更高分辨率，如768x1024像素或1024x768像素。

Examples

dreamlike.art

可以随便使用 dreamlike.art! ❗ 🔄

CKPT

Download dreamlike-photoreal-2.0.ckpt (2.13GB) ❗ 🔄

Safetensors

Download dreamlike-photoreal-2.0.safetensors (2.13GB) ❗ 🔄

🧨 Diffusers ❗ 🔄

This model can be used just like any other Stable Diffusion model. For more information, please have a look at the Stable Diffusion Pipeline. ❗ 🔄

from diffusers import StableDiffusionPipeline
import torch

model_id = "dreamlike-art/dreamlike-photoreal-2.0"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")

prompt = "photo, a church in the middle of a field of crops, bright cinematic lighting, gopro, fisheye lens"
image = pipe(prompt).images[0]

image.save("./result.jpg")