[tshaddox]

What are the leading alternatives? (Open source or otherwise)

[vunderba]

You have to be specific. What's more important to you?

- uncensored output (SD + LoRa)

- Overall speed of generation (midjourney)

- Image quality (probably midjourney, or an SDXL checkpoint + upscaler)

- Prompt adherence (flux, DALL-E 3)

EDIT: This is strictly around image generation. The main video competitors are Kling, Hailuo, and Runway.

[sebazzz]

SD does not generate video, does it?

[xvector]

https://stable-diffusion-art.com/animatediff/

[CryptoBanker]

It does as of recently.

[amrrs]

Minimax (from China) and Kling 1.5 from China. Recently Tencent launched its own.

You can see more model samples heee https://youtu.be/bCAV_9O1ioc

[ztratar]

Those look... far worse? What am I missing.

[amrrs]

Exactly I don't know how people are saying SORA is bad. I know there are restrictions with humans. But with the storyboard and other customisations, it's definitely up there!

[stuckkeys]

FLUX

[elorant]

MidJourney (commercial), Standard Diffusion XL

[aruametello]

> Standard Diffusion XL

you probably meant Stable Diffusion XL. (autocorrect victim)