AfterDark for Krea 2, Z-Image Turbo & Flux.2 Klein

This LoRA enhances your images with more punch, contrast, depth of field, and lighting. It's been trained on a mixture of photographic content with a focus on low-key, film noir, and fashion photography. It makes things pop without destroying image quality (in fact, it often enhances quality).

Suggested Krea 2 Turbo Settings
Model strength: 0.5-0.9
Samplers/schedulers:

• dpm_2_ancestral / ddim_uniform (or sgm_uniform)

• exp_heun_2_x0 / ddim_uniform

• euler / beta57 (or beta)

Suggested Z-Image Turbo Settings
Model strength: 0.3-0.8
Samplers/schedulers:

• seeds_3 / beta

• ddim / kl_optimal (or beta)

• dpm_2_ancestral / sgm_uniform (or ddim_uniform)

Suggested Flux.2 Klein 9b Settings
Model strength: 0.3-1.2
Samplers:

• res_multistep

• sa_solver

• seeds_3

• er_sde

• ddim

• ...and so many more

Distilled
Cfg Scale: 1-1.5
Steps: 8-10
Base
Cfg scale: 2.5-4
Steps: 40-55

This LoRA works with both Flux.2 Klein 9b base and distilled. I often use the distilled version because it generates images much faster and the quality is still really good.

v2 LoRA Technical Details

The Krea 2 Turbo LoRA ended up with a loss value of 0.09540. I took step 750, but did train to 1,500 steps and compared all of them. They all looked great so it wasn't an easy choice.
The Z-Image Turbo LoRA ended up with a loss value around 0.336 (this compares to v1 at around 0.71).
The Flux.2 Klein 9B LoRA ended up with a loss value of 0.5129 (5.129e-01). It was a "low and slow" train with a low learning rate (5.0e-05) over 6,000 steps. This was much longer than the Z-Image Turbo LoRA's training, but I think it was worthwhile. I might use a more powerful GPU next time (I used an A40 for this one).

A lot of training time went into these models followed by a lot of testing. I decided to keep the same model listing on Civitai simply because they were both trained from the exact same dataset (same images and captions). The training for the Klein version in ai-toolkit started off the same as the Z-Image one. I soon learned that wasn't going to work for Flux.2 Klein 9b so I adjusted the settings.

Version 2 is very stable for both base models. In fact I find that I don't often like the distilled version of Klein 9b without this LoRA. Images are generally too bright for my taste and while you could apply a LUT or do post processing work on the images, I simply prefer to use this LoRA because it does more than just lighting.