ELLA
ELLA copied to clipboard
ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment
Hi, will it be possible to support Stable Diffusion 3, at least judging by its research paper? If so, could you please update the training code and the models if...
Does it support stable diffusion 3?
Hello, thanks for your great work. I'm curious about the effect of training data. Did you ever directly fully fine-tune the SD-1.5 or SD-XL model on the training data? I...
Stable Cascade is currently the newest released diffusion model from StabilityAI. It has 3.6b parameters. That makes it bigger than SDXL. The unusually high latent compression makes this model special....
Very nice design, and I am not a ML engineer. I would like to ask if I can use use ELLA to extend the Prompt in multiple languages. previous sd...
There's been occasional attempts to pass [AstralCodexTen's image generation challenge](https://www.surgehq.ai/blog/dalle-3-and-midjourney-fail-astral-codex-tens-image-generation-bet) (from 2022!), but no one is quite there yet. > 1. A stained glass picture of a woman in a...
https://github.com/tianshuo/Impossible-AIGC-Benchmark See the benchmark here, which tests AIGC for prompt adherence.
ELLA 后出来的embedding 和diffusion model的 alignment 表现是怎么表现的,可以讲一下吗?谢谢~
First of all, I would like to express my sincere gratitude for your open-source model ELLA, which is truly remarkable. I have been closely following your team's work, and as...