TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Instruction-Based Image Editing via LLM

98 pointsby phrontover 1 year ago

7 comments

JamilDover 1 year ago
What&#x27;s interesting to me is that the project feels very &quot;un-Apple&quot;, 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:&#x2F;&#x2F;github.com&#x2F;apple&#x2F;ml-mgie&#x2F;blob&#x2F;main&#x2F;demo.ipynb">https:&#x2F;&#x2F;github.com&#x2F;apple&#x2F;ml-mgie&#x2F;blob&#x2F;main&#x2F;demo.ipynb</a><p>Apple truly becoming an ML company when they release ML Engineer quality code ;)
评论 #39281707 未加载
kkukshtelover 1 year ago
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&#x27;t great) and really you just want to explore the latent space &quot;around&quot; an initial prompt.<p>Here&#x27;s an overview of the tool (Dreamwalker): <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=k_mJgFmdWWY" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=k_mJgFmdWWY</a><p>And you can download&#x2F;use it for free here (mac&#x2F;pc): <a href="https:&#x2F;&#x2F;forums.afterschool.studio&#x2F;t&#x2F;dreamwalker-alpha-2-release&#x2F;66" rel="nofollow">https:&#x2F;&#x2F;forums.afterschool.studio&#x2F;t&#x2F;dreamwalker-alpha-2-rele...</a>
achalkleyover 1 year ago
It&#x27;s incredible to see Apple contributing here. Excited to see what they bring to their platforms.
评论 #39278956 未加载
itakeover 1 year ago
I wish they had more examples. the image doesn&#x27;t seem to be that much better than if you generate an image with stable diffusion and then tweak the prompt.
rodoxcastaover 1 year ago
&gt; Notices: Apple&#x27;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&#x27;t the finetuning be a modification of the original work and so have the same license?
评论 #39285996 未加载
vunderbaover 1 year ago
How similar is this to InstructPix2Pix?<p><a href="https:&#x2F;&#x2F;github.com&#x2F;timothybrooks&#x2F;instruct-pix2pix">https:&#x2F;&#x2F;github.com&#x2F;timothybrooks&#x2F;instruct-pix2pix</a>
stcredzeroover 1 year ago
Has there been any work done on charts, graphs, and data visualizations produced by large AI generative models?
评论 #39279335 未加载