What's interesting to me is that the project feels very "un-Apple", despite being open-sourced under the Apple org; some typos and lack of proper punctuation in the README, using jupyter notebooks for the data processing instead of scripts or a CLI, poor repo organization, no comments even in the demo: <a href="https://github.com/apple/ml-mgie/blob/main/demo.ipynb">https://github.com/apple/ml-mgie/blob/main/demo.ipynb</a><p>Apple truly becoming an ML company when they release ML Engineer quality code ;)
I came up with a similar idea to this (also pre-Dalle edits-via-instruction) with the idea that prompting generators kinda sucks (also chat interfaces for image editing aren't great) and really you just want to explore the latent space "around" an initial prompt.<p>Here's an overview of the tool (Dreamwalker):
<a href="https://www.youtube.com/watch?v=k_mJgFmdWWY" rel="nofollow">https://www.youtube.com/watch?v=k_mJgFmdWWY</a><p>And you can download/use it for free here (mac/pc):
<a href="https://forums.afterschool.studio/t/dreamwalker-alpha-2-release/66" rel="nofollow">https://forums.afterschool.studio/t/dreamwalker-alpha-2-rele...</a>
I wish they had more examples. the image doesn't seem to be that much better than if you generate an image with stable diffusion and then tweak the prompt.
> Notices: Apple's rights in the attached weight differentials are hereby licensed under the CC-BY-NC license. Apple makes no representations with regards to LLaMa or any other third party software, which are subject to their own terms.<p>Wait, they can do that? Assuming weights have copyright, shouldn't the finetuning be a modification of the original work and so have the same license?
How similar is this to InstructPix2Pix?<p><a href="https://github.com/timothybrooks/instruct-pix2pix">https://github.com/timothybrooks/instruct-pix2pix</a>