It seems that #comfyui in the cloud has become available to everyone, not just beta testers. The price is $20 per month, and this subscription includes $10 worth of API nodes (which is very good if you use them, I do), so it's like a $10 bonus, if I understand correctly. There are also limits: no more than 8 GPU hours per day (it's hard for me to estimate how much that is, but it seems like a lot) and no more than 30 actual minutes per job (to exceed that, you'd have to do some serious animation or batch rendering of something). All of this runs on A100 with 40Gb VRAM (i.e., like Google Colab). The ability to upload your own models is listed as coming soon, as is the ability to run multiple jobs in parallel. Custom nodes currently includes the 10 most popular packages, but will clearly be expanded in the future.

What it can be useful for at this stage of development:
- Upscale (a difficult task for a local machine if you don't have a 4090 or 5090, and it doesn't require your own LoRA, which cannot be uploaded to comfy cloud yet)
- Animation using WAN (also difficult to run locally, but the quality is quite good; for $20 a month, it would be hard to find anything better)
- Image editing via qwen image (this task runs well locally if you have 16GB VRAM, but if you don't, it makes sense to work in the cloud)

For the local version, everything remains the same; it is still free, as it was before.

https://www.comfy.org/cloud

This Saturday, I want to host an open webinar dedicated to comparing generative AI models for architectural tasks.
https://www.youtube.com/live/XTLtcx9JrcI?si=fHcZ04IOI0jSCAsK

- Details: I will take some of the coolest AI models available at the moment and show how they handle tasks such as AI rendering, Inpaint, or inserting objects into a scene. The set of models will vary slightly for different tasks. Our goal will be to find out what in general can be done with AI to generate images in architecture, and which combination of models and tools is currently most relevant for solving a particular task.

- It starts on Saturday night (the hour depends on your time zone; if you open YouTube, it'll show the exact time for you).

- I'll try to do it in English (I'm not great with languages, but I hope it'll be understandable).

- the duration will probably be about an hour, or maybe two or five, whichever works out

- of course, it's free and there will be a recording (at the same link as in this post) if you can't join the live stream. But it's better to join, and I'll be happier, and you'll be able to ask questions.

#education #ai #comfyui

It seems that the classic approach to visualization has already become less relevant, and in a couple of years it will only be needed for very accurate and specialized renders. I mean, in my experience, AI rendering is already close to perfection. You can see one example in this video.

#comfyui #gemini