A versatile photorealistic checkpoint

Built for high-quality artistic and creative image generation.

It delivers strong results across a wide range of styles and subjects, with excellent anatomy, lighting, skin detail, and overall coherence. Fully capable of both refined SFW artistic work and high-quality NSFW content.

Recomended Models (civitai does not let me order them)

Similar for MOSS fp16 first -> int8 second

Why SDXL, Krea 2, MOSS?

These are the most flexible models that can handle both SFW and NSFW without losing too much detail. I tried Flux, ZIT, and similar models — nothing came close to the results I got with SDXL, Krea 2 and MOSS. So I maxed out my SDXL model and began working on Krea 2 and now made a MOSS version.

NOTE: INT8 version is a bit faster on older GPU's the output is recognizably different, but people and scene in general looks similar to fp16/fp8 (the output is better or worse than fp16/fp8 based on the seed and prompt).

Recommended Settings

SDXL

• Steps: 40

• CFG Scale: 5.5

• Sampler: exp_heun_2_x0_sde

• Scheduler: gits

• Resolution: 832 × 1216 (2:3)

Krea 2 Turbo (Recommended over Full because it is faster and looks better IMO)

• Steps: 8

• CFG Scale: 1.0 (after a bit of experimentation this value can be set between 0.925 - 1.075 and result can be better or worse)

• Sampler: exp_heun_2_x0_sde > euler > euler_cfg_pp > euler_ancestral_cfg_pp and LCM shows promise

• Scheduler: sgm_uniform > beta_1_1 > normal/simple, and maybe ays_30

• Resolution: 832 × 1216 (2:3)

Krea 2 Full (Alternative option, best avoid)

• Steps: 20+ (very slow so higher means more time to generate)

• CFG Scale: 4+ (not sure here, same for Sampler + Scheduler)

• Resolution: 832 × 1216 (2:3)

Krea 2 Advanced

Text Encoder (Abliterated): https://civarchive.com/models/2731465/qwen3-vl-4b-abliterated-comfyui-krea-2-text-encoder-bf16-fp8?modelVersionId=3070870

VAE (Clear): https://civarchive.com/models/2151326/qwen-imageclearvae

Note: You can use the text encoder and VAE either separately or together, depending on the result you want. The text encoder changes the output significantly (use with caution), while the VAE mainly affects contrast which can be beneficial or undesirable depending on the image (I would probably avoid the VAE for photorealistic amateur-style images that are intentionally meant to look low-quality and low-contrast).

Krea Gone Wild (1.0-2.0)

Play with this (if you have it) to get a different output when all else fails to produce what you want.

Comparison FP8 (left) vs FP16 (right) model versions

MOSS Image (SFT):

• Steps: 20+

• CFG Scale: 3.5+ (needs more testing)

• Sampler: exp_heun_2_x0_sde (others)

• Scheduler: sgm_uniform (others)

• Resolution: 832 × 1216 (2:3)

This is one of the most NSFW options, still prefer Krea 2 for less errors, but for unhinged NSFW this is a very promising model.

MOSS Note: Some Asian bias in the model so prompt for exactly what you want like ex. European and problem solved.

MOSS Advanced:

Text Encoder (Abliterated): https://huggingface.co/DrHippie/qwen3.5-9b_abliterated_0x100refusal_vision_int8_convrot/tree/main

Comparison SDXL/Krea2/MOSS:

Credits

Includes a small contribution from Detail Slider - (Krea 2) by Loraholic See: https://civarchive.com/models/2772451

The model is otherwise my own fine-tune and merge work, with a massive amount of fine-tuning.

License

• krea-2-community-license