TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

DALL-E Mini – Generate images from a text prompt

52 点作者 tuhins将近 3 年前

9 条评论

__rito__将近 3 年前
Wow, this author is very dishonest as it does not mention any of the people who created this project in the first place. I was one of the people who worked in this project.<p>This was spearheaded by Boris Dayma, now at Weights and Biases.<p>This is an Open Source project with all code and methods in public.<p>See either GitHub (<a href="https:&#x2F;&#x2F;github.com&#x2F;borisdayma&#x2F;dalle-mini" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;borisdayma&#x2F;dalle-mini</a>) or the hosted space in Hugging Face Hub (<a href="https:&#x2F;&#x2F;huggingface.co&#x2F;spaces&#x2F;dalle-mini&#x2F;dalle-mini" rel="nofollow">https:&#x2F;&#x2F;huggingface.co&#x2F;spaces&#x2F;dalle-mini&#x2F;dalle-mini</a>) or the project report (<a href="https:&#x2F;&#x2F;wandb.ai&#x2F;dalle-mini&#x2F;dalle-mini&#x2F;reports&#x2F;DALL-E-mini-Generate-images-from-any-text-prompt--VmlldzoyMDE4NDAy" rel="nofollow">https:&#x2F;&#x2F;wandb.ai&#x2F;dalle-mini&#x2F;dalle-mini&#x2F;reports&#x2F;DALL-E-mini-G...</a>).<p>This project was also covered in the NYT article on Dalle2 by Cade Metz.<p>The author gives no credits at all. That is apalling.<p>(Also, the one hosted in the HF Hub gives you better results)<p>I just realized that this person is either using our model (some point in the past) and not giving us due credit, or they trained a new model and the name just happens to match.<p>In the latter case, please ignore my rant and use my links as a reference to another project than the claim that this prpject is our project.
smcleod将近 3 年前
This one seems really poor compared to the other minis I&#x27;ve tried. Mostly unrecognisable, blurred shapes
评论 #31704578 未加载
评论 #31702542 未加载
wbraun将近 3 年前
Are there different variants of DALL-E Mini? Running prompts through both this version and the one hosted on huggingface gives noticeably different results. The one on huggingface seems to give more accurate responses.
评论 #31705432 未加载
masswerk将近 3 年前
Interesting results: I tried &quot;a train entering a station&quot; and &quot;a train in the countryside&quot;. Both images showed a track with rails and some kind of distortion (somewhat reminiscent of speed, more so the first one), but no train, omitting the subject in favour of circumstances.<p>So, a touch of Rain, Speed and Steam?<p>So I tried &quot;a train speeding in rain&quot; and got a somewhat car-like out of the window view on a rainy landscape, with a hint of rails somewhat mangled into what looked more like a road for automobiles to me. — However, no Turner… ;-)
scottlawson将近 3 年前
I tried<p>a green bowl a green bowl with an apple a green bowl with an apple inside a banana in a bowl<p>the only one that seemed correct was &quot;a green bowl&quot;, all of the others were very different.
jerpint将近 3 年前
How is this different from dall-e mini on huggingface?
评论 #31701641 未加载
userbinator将近 3 年前
The results are amusing but not particularly accurate; &quot;cat&quot; resulted in a recognisable but distorted cat, &quot;dog&quot; produced a barely recognisable nightmarish blob of fur and eyes, and &quot;pig&quot; output something with nothing more than the general texture of a pig.
ncr100将近 3 年前
Check out the horror show that is &quot;carrot top comedian&quot;.<p>For out of four queries resulted in synthetic portraits that are terrifically scary.
athorax将近 3 年前
Mostly just getting unrecognizable blobs
评论 #31701322 未加载
评论 #31701823 未加载