Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

I tried it now.

My experience:

Took 4 minutes to log in and do one generation. (Login to FB, then it took me through a process to merge accounts with Meta, which didn't sound good, so I restarted with 'sign in via email' which ended up doing the same thing anyway, I think. Then I was logged in, did the generation.)

My at a glance is that it's:

For image quality

1. Midjourney

2. Dall e 3

3. SDXL and this

For overall ease of use and convenience

1. Dall e 3

2. Midjourney

Of course, this is all biased personal opinion, and YMMV.



Depends what you want really, Midjourney and Dall-E 3 have specific looks to them which kind of look cheap/tacky now its everywhere.

SDXL is reconfigurable and completely flexible so really its the only tool in the game for pure creativity.


For hackernews users definitely comfyui. Good place to start playing arround with tlcheckpoints, loras, controlnets and ipadapters.


What is the best tool wrapping SDXL


There is no best, it depends on your usecase. Auto1111 is popular, ComfyUI extremely flexible but complex, and there is a myriad of other wrappers, some with a focus on simplicity, some not so much.


Depends what you mean by "best", but Fooocus is very accessible for getting started with Stable Diffusion.


I find Automatic1111 better for point and click simplicity. ComfyUI has been good for custom flows.

Also Automatic1111 is more centralized, so you have to wait for something to make its way in (or a pull request for it anyhow), whereas people put up their ComfyUI custom JSON workflows. So I am doing Stable Diffusion video via ComfyUI right now, whereas it has not made its way into Automatic1111.


On Windows, StabilityMatrix (https://github.com/LykosAI/StabilityMatrix) is a very easy way to get any (or all) of those wrappers installed without conflicts.


Btw, automatic1111 was made by a racist rimworld mod author, and directly cites 4chan as being a primary contributor!

Fun world we live in.


Like it or not 4chan's technology forum is one of the forefronts of local image gen/voice/llm model discussions, this is why the most prominent SD interface is written by a 4chan poster.

Considering the author of ComfyUI is called ComfyAnonymous and has an anime avatar it's very likely they're a 4chan poster too so maybe don't use that if it actually bothers you.

Both are very good tools for using this stuff on the cutting edge so I couldn't really care less what the authors do in their free time.


Honestly I don’t care either (about the 4chan connection anyway), but it’s a fun fact I like to roll out which surprises people

Also his rimworld mods are indefensible. A Kenosha mod about “peaceful protest” where exclusively black pawns continuously attack your colony? That’s racist bro! It’s only flown under the radar because rimworld is played mostly by individuals with ASD.


Fooocus is fantastic for working out of the box.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: