|
Saoirse Ronan embedding created by Airathias Usage of a VAE highly advised, it likes to make the pupils huge and blobby. Embedding was created in 800 steps, and a large number of vectors per token so keep your prompt short and concise. I've only seen weird results with long prompts, and anything very anime-ish. Anything resembling realism will render just fine. I added prompts to a few of the example images, should work fine. These prompts were basically blatantly copied from other examples throughout the website. If I copied yours, mea culpa. You can use this without crediting me. The embedding was trained on stock SD 1.5, so it should work for many if not most models based off of 1.5. Images listed are made using a handful of models to test, including: | 
发表于 2023-6-7 22:42:18