Comments (9)
chairc
commented on July 20, 2024
一般来说我们只训练64×64的模型，然后在此基础上生成256×256的图像。我们最多跑160×160的尺寸，22GB显存。群里有人用10张3090跑了80多个小时的256×256训练
from integrated-design-diffusion-model.
egoist945402376
commented on July 20, 2024
一般来说我们只训练64×64的模型，然后在此基础上生成256×256的图像。我们最多跑160×160的尺寸，22GB显存。群里有人用10张3090跑了80多个小时的256×256训练
佬, Latent方式降低显存功能大概多久能上啊, 很期待_(:з)∠)_. 这样就能生成和训练更大的尺寸了 GitHub上好像没有什么公开可以自己训练的潜在扩散模型. 就你这一家了, 全村的希望
from integrated-design-diffusion-model.
chairc
commented on July 20, 2024
得等我有时间慢慢弄，现在在看着咋搞呢，估计要重写train方法
from integrated-design-diffusion-model.
egoist945402376
commented on July 20, 2024
得等我有时间慢慢弄，现在在看着咋搞呢，估计要重写train方法
大佬辛苦了
from integrated-design-diffusion-model.
egoist945402376
commented on July 20, 2024
一般来说我们只训练64×64的模型，然后在此基础上生成256×256的图像。我们最多跑160×160的尺寸，22GB显存。群里有人用10张3090跑了80多个小时的256×256训练
大佬我刚刚试着在generate.py里把img_size调成256, 直接报OOM, 要64GiB的显存, 而且只能放在单卡上, 用的是ddim, UNET, 预加载的模型是cifar10-conditional-ddim-unet-gelu-numclass10-imagesize64_model.pt, 只生成一张, 请问有什么可以降低需求的方法吗.
from integrated-design-diffusion-model.
chairc
commented on July 20, 2024
算力需要大显存，硬性条件。256×256计算量很大，你可以先用64×64的模型跑出来你可以生成最大的图，再自己写个resize方法上采样扩大尺寸吧。
from integrated-design-diffusion-model.
egoist945402376
commented on July 20, 2024
哥你这么晚还在. 谢谢哥, 所以一般是生成自己能生成最大的再用torchvision resize就好了嘛.
from integrated-design-diffusion-model.
yhchen07
commented on July 20, 2024
一般来说我们只训练64×64的模型，然后在此基础上生成256×256的图像。我们最多跑160×160的尺寸，22GB显存。群里有人用10张3090跑了80多个小时的256×256训练
请问作者可以分享一下10张3090的256x256训练的train.py里的参数设置吗, 非常感谢
from integrated-design-diffusion-model.
chairc
commented on July 20, 2024
还有就是用超分算法去扩或者清晰化图像
from integrated-design-diffusion-model.
Related Issues (14)
- 可以用来生成工业上的缺陷图片吗？ HOT 4
- 写地太神了, 作为新手仍然想慢慢读源码 HOT 1
- 数据集是否需要划分 HOT 5
- 输入的是灰度图像 能输出灰度图像吗 HOT 3
- cifar-10 调参 HOT 1
- 租用的GPU训练时出现socket has failed to listen on any local network address HOT 1
- 恢复训练 HOT 1
- 請問支援prompt輸入嗎? HOT 1
- 咨询 HOT 4
- 关于训练集和验证集 HOT 2
- 生成出来的图片是噪点图 HOT 5
- 如有任何问题，可以加入群聊交流，Q群号：949120343 HOT 2
- A summary of issues (问题总结) HOT 11
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from integrated-design-diffusion-model.