Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

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

mlblocks.com

Post reply on HN
Print view View original

21–30 of 33 posts

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

#21

Post by neilxm »

cchu wrote: post #9
neilxm wrote: post #4

Earlier quoted context omitted.

Nice! Sharing workflows is coming up in approximately 2 sprints. We're working on 2 flavors of sharing. The first is sharing the workflow directly and letting someone copy it for the dev community. The more interesting option though is the second, where we'll let you build a read-only dashboard that will just show inputs and outputs. that should be useful when you share it with a marketing team that doesn't need to m…

This is great and totally agree with the above comment. I think it's a really useful next step up from someone who is comfortable with prompts but wants a bit more control or having a resusable workflow. It'd be cool if there can also be more premade "recipes" as a starting point to modify/extend. Then hitting the play button gives you something right away. Also kudos to whoever made the fun little tilt animations on…

We're working on shareable graphs and premade recipes! I actually started sharing a few on our blog - here's an example: https://blog.mlblocks.com/p/auto-generate-banner-images-for-...

haha, the tilt animations are a by-product of my obsession with Trello. :)

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

#22

Post by echelon »

starwaver wrote: post #3

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't have to wrangle with coding and instead focusing experimenting with different nodes. However soon creating a "shader that works" was no longer an issue but how to create X effect using shaders was my next blocker, and lu…

Check out ComfyUI for a much more advanced and open source version of this.

https://github.com/comfyanonymous/ComfyUI

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

#23

Post by echelon »

itake wrote: post #14
ljouhet wrote: post #12

Sorry to write this comment: isn't it exactly like ComfyUI?

Comfyui is just for interacting with stable diffusion. This supports other models.

ComfyUI is adding lots of other models. And it's open source and much further along.

https://github.com/comfyanonymous/ComfyUI

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

#24

Post by pj_mukh »

echelon wrote: post #22
starwaver wrote: post #3

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't have to wrangle with coding and instead focusing experimenting with different nodes. However soon creating a "shader that works" was no longer an issue but how to create X effect using shaders was my next blocker, and lu…

Check out ComfyUI for a much more advanced and open source version of this. https://github.com/comfyanonymous/ComfyUI

Not really an apples-to-apples comparison. ComfyUI is for diffusion-focused workflows, this is not.

Plus you don't need a local GPU for this. I realize this is a Pro for some Con for others, so there can be different products in the market serving different needs.

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

#26

Post by lancesells »

pj_mukh wrote: post #7
chaoz_ wrote: post #5

Love the idea, however, it'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.

Theoretically, most OpenCV-type image pre/post-processing stuff is available in blocks and then all the major multi-modal + diffusion AI blocks are also available. As a sampling of what we've recently added: AI Blocks: - Multimodal LLM (GPT4v) - Remove objects in Images - AI Upscale 4x - Prompted Segmentation (SAM w/ text prompting) Editing Blocks: - Change format - Rotate - Invert Color - Blur - Resize - Mask to Alp…

Is this all AI or using something like Imagemagick for the lower level tasks?

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

#27

Post by neilxm »

lancesells wrote: post #26
pj_mukh wrote: post #7

Earlier quoted context omitted.

Theoretically, most OpenCV-type image pre/post-processing stuff is available in blocks and then all the major multi-modal + diffusion AI blocks are also available. As a sampling of what we've recently added: AI Blocks: - Multimodal LLM (GPT4v) - Remove objects in Images - AI Upscale 4x - Prompted Segmentation (SAM w/ text prompting) Editing Blocks: - Change format - Rotate - Invert Color - Blur - Resize - Mask to Alp…

Is this all AI or using something like Imagemagick for the lower level tasks?

It's a combination of things. The idea is that you can build workflows that chain functionality from ai models, as well as lower level image processing tasks. For lower level tasks we use the usual suspects - PIL, ImageMagik, OpenCV etc.

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

#30

Post by sgrove »

Interesting! Always interesting to see the ideas in the air at the same time!

https://linzumi.com/

Definitely think this sort of idea could become the "serverless" equivalent for ml-using apps. I'm curious what you think re: versioning, consumption from various client languages, observability/monitoring/queueing, etc.? Feels like it could grow into a meaningful platform.

Post reply on HN