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://github.com/borisdayma/dalle-mini" rel="nofollow">https://github.com/borisdayma/dalle-mini</a>) or the hosted space in Hugging Face Hub (<a href="https://huggingface.co/spaces/dalle-mini/dalle-mini" rel="nofollow">https://huggingface.co/spaces/dalle-mini/dalle-mini</a>) or the project report (<a href="https://wandb.ai/dalle-mini/dalle-mini/reports/DALL-E-mini-Generate-images-from-any-text-prompt--VmlldzoyMDE4NDAy" rel="nofollow">https://wandb.ai/dalle-mini/dalle-mini/reports/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.
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.
Interesting results: I tried "a train entering a station" and "a train in the countryside". 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 "a train speeding in rain" 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… ;-)
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 "a green bowl", all of the others were very different.
The results are amusing but not particularly accurate; "cat" resulted in a recognisable but distorted cat, "dog" produced a barely recognisable nightmarish blob of fur and eyes, and "pig" output something with nothing more than the general texture of a pig.
Check out the horror show that is "carrot top comedian".<p>For out of four queries resulted in synthetic portraits that are terrifically scary.