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

Comparing Adobe Firefly, Dalle-2, and OpenJourney

blog.usmanity.com

Post reply on HN
Print view View original

31–40 of 139 posts

Re: Comparing Adobe Firefly, Dalle-2, and OpenJourney

#31

Post by Sharlin »

famouswaffles wrote: post #17
gwern wrote: post #10

Earlier quoted context omitted.

The stagnation has been very curious. They are part of a large & generally competent org, which otherwise has remained far ahead of the competition, like GPT-4. Except... for DALL-E 2, where it did not just stagnate for over a year (on top of its bizarre blindspots like garbage anime generation), but actually seemed to get worse . They have an experimental model of some sort that some people have access to, but even…

Nobody is able to use Parti or eDiff. Compared to models you can use, the experimental Dall-e or Bing Image Creator is second only to midjourney in my experience.

I haven't tried those two, but I'd be surprised if they were better than Stable Diffusion. Which is free, runnable (and trainable!) locally, and already has a large ecosystem of frontends, tweaks and customized models.

Re: Comparing Adobe Firefly, Dalle-2, and OpenJourney

#33

Post by bluetidepro »

kouteiheika wrote: post #16

For reference, here's what you can get with a properly tweaked Stable Diffusion, all running locally on my PC. Can be set up on almost any PC with a mid range GPU in a few minutes if you know what you're doing. I didn't do any cherry picking; this is the first thing it generated. 4 images per prompt. 1st prompt: https://i.postimg.cc/T3nZ9bQy/1st.png 2nd prompt: https://i.postimg.cc/XNFm3dSs/2nd.png 3rd prompt: https:…

Do you have any good tutorial links to setup Stable Diffusion locally?

Re: Comparing Adobe Firefly, Dalle-2, and OpenJourney

#34

Post by muhammadusman »

mdorazio wrote: post #32

Since the author didn't have access to Midjourney, here's the first two prompts in MJ with default settings (not upscaled): https://imgur.com/a/siQG06O https://imgur.com/a/vp2oOHu

thanks for sharing this, do you mind if I include this in the post. I will credit you of course (let me know what you'd like linked to).

update: I've edited the post to include these results as well

Re: Comparing Adobe Firefly, Dalle-2, and OpenJourney

#36

Post by throwaway20222 »

kouteiheika wrote: post #19
jamilton wrote: post #12

Earlier quoted context omitted.

None of these can do text well. There's a model that does do text and composition well, but the name escapes me. And the general quality is much lower overall, so it's a pretty heavy tradeoff.

DeepFloyd? https://github.com/deep-floyd/IF

I believe this is at least one solution, and one that the folks at stability themselves were pushing hard as a next step forward in the development of LLMs.

Re: Comparing Adobe Firefly, Dalle-2, and OpenJourney

#38

Post by muhammadusman »

kouteiheika wrote: post #16

For reference, here's what you can get with a properly tweaked Stable Diffusion, all running locally on my PC. Can be set up on almost any PC with a mid range GPU in a few minutes if you know what you're doing. I didn't do any cherry picking; this is the first thing it generated. 4 images per prompt. 1st prompt: https://i.postimg.cc/T3nZ9bQy/1st.png 2nd prompt: https://i.postimg.cc/XNFm3dSs/2nd.png 3rd prompt: https:…

thanks for doing this, I would like to include these into the blog post as well. Can I use these and credit you for them? (let me know what you'd like linked)

Re: Comparing Adobe Firefly, Dalle-2, and OpenJourney

#39

Post by ewjt »

kouteiheika wrote: post #16

For reference, here's what you can get with a properly tweaked Stable Diffusion, all running locally on my PC. Can be set up on almost any PC with a mid range GPU in a few minutes if you know what you're doing. I didn't do any cherry picking; this is the first thing it generated. 4 images per prompt. 1st prompt: https://i.postimg.cc/T3nZ9bQy/1st.png 2nd prompt: https://i.postimg.cc/XNFm3dSs/2nd.png 3rd prompt: https:…

Can you elaborate on “properly tweaked”? When I use one of the Stable Diffusion and AUTOMATIC1111 templates on runpod.io, the results are absolutely worthless.

This is using some of the popular prompts you can find on sites like prompthero that show amazing examples.

It’s been serious expectation vs. reality disappointment for me and so I just pay the MidJourney or DALL-E fees.

Post reply on HN