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.

Show HN: ML Blocks – Deploy multimodal AI workflows without code

112 pointsby neilxmover 1 year ago
Hey everyone,<p>ML Blocks is a node-based workflow builder to create multi-modal AI workflows without writing any code.<p>You connect blocks that call various visual models like GPT4v, Segment Anything, Dino etc. along with basic image processing blocks like resize, invert color, blur, crop, and several others.<p>The idea is to make it easier to deploy multi-step image processing workflows, without needing to spin up endless custom OpenCV cloud functions to glue together AI models. Usually, even if you&#x27;re using cloud inference servers like Replicate, you still need to write your own image processing code to pre and post-process images in your pipeline. When you&#x27;re trying to move fast, that&#x27;s just unnecessary overhead.<p>With ML Blocks, you can build a workflow and deploy the whole thing as a single API. AFAIK, ML Blocks is the only end-to-end workflow builder built specifically for image processing.<p>If you&#x27;re curious, our models run on Replicate, HuggingFace &amp; Modal Labs cloud GPUs and we use React Flow for the node UX.

9 comments

starwaverover 1 year ago
I like the idea of node based image editing. It reminds me of when learning how to write shader code for games and GLSL was waaaay too over my head until I discovered node based shaders, and I didn&#x27;t have to wrangle with coding and instead focusing experimenting with different nodes.<p>However soon creating a &quot;shader that works&quot; was no longer an issue but how to create X effect using shaders was my next blocker, and luckily there were ton of YouTube tutorials on these, which was very helpful, but this continues to be a pain point even now<p>Since now we are in the age of AI, would it be possible to prompt something like &quot;create me a workflow to take image A, a concept art of a character and convert into into a walking animation sprite sheet with 16 frames for each animation walking up, down, left, right and all diagonal directions&quot; and have it not only generate the result, but a workflow to create the result so it can be edited and tweaked.
评论 #39218613 未加载
评论 #39223842 未加载
评论 #39218847 未加载
评论 #39219445 未加载
ljouhetover 1 year ago
Sorry to write this comment: isn&#x27;t it exactly like ComfyUI?
评论 #39219053 未加载
评论 #39219070 未加载
评论 #39218971 未加载
sgroveover 1 year ago
Interesting! Always interesting to see the ideas in the air at the same time!<p><a href="https:&#x2F;&#x2F;linzumi.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;linzumi.com&#x2F;</a><p>Definitely think this sort of idea could become the &quot;serverless&quot; equivalent for ml-using apps. I&#x27;m curious what you think re: versioning, consumption from various client languages, observability&#x2F;monitoring&#x2F;queueing, etc.? Feels like it could grow into a meaningful platform.
评论 #39225236 未加载
syed99over 1 year ago
I had a chance to play around with the product and I really love the ease of creating a multi step workflow, to the point where I&#x27;m sure I can train my marketing team to use it. That being said, is there a way to share these workflow with others...either privately or publicly?
评论 #39218509 未加载
esfahaniover 1 year ago
This is amazing! Really helps with those of us who are just getting started building workflows for AI images for ecom. Are there any plans to add bulk processing capabilities, allowing workflows to run on multiple images automatically without manual UI interactions?
评论 #39219166 未加载
chaoz_over 1 year ago
Love the idea, however, it&#x27;s not clear whether I will get access to a large collection of components for building such workflows or what is currently possible? Would nice to get this info before proceeding with auth.
评论 #39218665 未加载
评论 #39218693 未加载
moralestapiaover 1 year ago
Hey, this is really cool!<p>A small suggestion, I don&#x27;t think ML is a memorable term for non-technical people. I would prob. try a different name.
评论 #39225214 未加载
genmanover 1 year ago
This concept is widely used in video editing and visual effects.
评论 #39221484 未加载
animal_spiritsover 1 year ago
Very cool, looking forward to seeing this evolve
评论 #39219068 未加载