ChatGPT's 1-Year Anniversary: Are Open-Source Large Language Models Catching Up?

Re:ChatGPT's 1-Year Anniversary: Are Open-Source Large Langu... by mattnewton on Thursday November 30, 2023 @11:13PM (#38483055)

SDXL has controlnet for other kinds of non-text input (like scribbles or just masks). The results are much easier to control in my opinion (a picture is worth thousands of prompt words).

For pure prompt coherence though I think ideogram is not far behind dalle 3.

[ Parent | on HN ]

Re:ChatGPT's 1-Year Anniversary: Are Open-Source Large Langu... by vunderba on Friday December 01, 2023 @12:02AM (#38483342)

EDIT: okay, I just tried Ideogram. It's not terrible and seems to do an okay job on text generation but I'd still say its a distant second compared to DALL-E 3. However, having the ability to maintain image continuity to make refinements of your initial image based on corrections like: "Make the building larger", or "He should have a more prominent forehead" is a game changer (e.g. InstructPix2Pix) and DALL-E 3's the only one that's got it.

Ideogram comparisons at bottom:

https://imgur.com/a/2GTRjfK

[ Parent | on HN ]

Re:ChatGPT's 1-Year Anniversary: Are Open-Source Large Langu... by vunderba on Thursday November 30, 2023 @11:18PM (#38483078)

SDXL and even some SD 1.5 checkpoints are great. My current workflow is:

1. Generate initial draft image in DALL-E 3 (iterate as necessary)

It's essentially the ONLY good InstructPix2Pix model.

2. Bring into InvokeAI

Inpaint with stuff that might be considered censored in DALL-E 3.

I'd like to see some proof of Ideogram - it looks... very mobile/instagrammy from the landing page. If you have an account, try out my prompts I'd like to see what you're able to produce.

[ Parent | on HN ]