Zeitgeist – Photographic (Style LoRa for SDXL)

Please see the second image post I created for a comparison between Zeitgeist – Photographic and Base SDXL 1.0 using the same generation settings and prompts!

See here for an article about my training method to create near-perfect style and character LoRa’s for SDXL 1.0!

I highly recommend using this model with an upscaler workflow. I find that it can greatly increase the already great image quality – depending on the prompt. You can find such an example workflow in the first example image of this post (the one that serves as the thumbnail of this model).

Current version: v1.0 | Recommended weight: 1.0 – or lower when you combine it with other LoRa’s | Recommended VAE: SDXL 0.9 | Recommended model: SDXL 1.0 | Recommended settings: 35 steps | DPM++ 2M Karras | CFG 7 | Recommended negative prompt: text, watermark, signature, abstract, burned, instagram, low-quality, low-res, action figure, child drawing, jpeg, low contrast, glossy, puppet, cliché, stock photo, magazine cover (I have done a lot of testing with many dozens of prompt words and this is the best universal negative prompt I could find, all other common negative prompt words people use I found to have no or only a negative effect on the output)

I recommend using the official SDXL 1.0 model that has the SDXL 0.9 VAE already integrated, which you can find here.

Description

A photographic artstyle LoRa for SDXL 1.0, aimed at delivering a lightweight improvement upon SDXL by adding skin details, reducing the post-processing, and making outputs more consistent and diverse – depending on the prompt.

Trigger words

• “photo”

• “studio photo”

• “greyscale photo”

• “with beautiful lighting”

Current Issues

• Eyes don’t look good, might be fixable with inpainting or upscaling though

Changelog

v1.0

• Initial release

Additional Info

Credit is not mandatory but I would still appreciate credit when posting images using these LoRa’s on social media! Feel free to @ my Twitter and/or Instagram accounts too (@ai_characters)! I would love to know when it is used!

I share all of my model’s and training knowledge for free, but donations to my Ko-Fi would be greatly appreciated! Testing so much and training so many model’s costs a lot of money.

Feel free to also try out my RVC2 AI voice models which you can find here!

Stats

Dataset:

• 188x photos

Training times (for 100 epochs):

• Artstyle (at 2 repeats): ~4h [???s/it]

Epoch chosen for the final model:

• 35? 50? (I think? Sorry, I forgot!)