New -> Flux2Klein9b ULT PRO
SAMPLER: seeds_3 / exp_heun_2_x0_sde / Euler / Whatever works for YOU
STEPS: 4-20 (YES 4-20 - you control how much detail/veneer you want)
CFG: 1-3 (YES 1-3 - you can use NEG prompt now and improve overall consistency)
RESOLUTION - UP TO 1280x1920
LESS DEFAULT PUBIC HAIR (use dedicated LORA and/or prompting when needed)
can generate those male thingies now (on women too)
works GREAT on img2img - no need for NSFW/"make real" LORAs anymore
Previews in gallery look way worse than the real images!
How to see >REAL< quality (examples: >Flux2Klein< >ZIT< ):
Right-click image → Open image in new tab
In new tab: again Right-click image → Open image in new tab
Click image - it will magnify to it's true resolution
Idea behind Vintage Beauties models:
Real-looking hairy bodies that feel like actual film photos - grainy, soft, a bit imperfect and alive. Visible film grain, gentle glow in bright areas, creamy shadows, vintage lens quirks (like halation and swirl), plus subtle color shifts. Nothing clean, sterile or digital. Just raw, organic, breathing analog vibes. Experimental merges, so not perfect.
No cherry-picking or upscaling/refining - simple workflow for straightforward evaluation.
Each image in gallery was generated using the same seed.
Workflows and prompts are included in the images (dl and drag to ComfyUI)
Flux Klein 9b v2 is based on FLUX.2-klein-base-9B
Flux Klein 9b v1 is based on FLUX.2-klein-9B (distilled)
Both models work with txt2img and img2img
Both models work with LoRAs (tested with up to 3 + sliders)
Settings for FLUX.2-klein-9B V2 (model for rich natural detail that looks best at ~2 MP ~ full HD)
SAMPLER: exp_heun_2_x0_sde (top choice for this model)
STEPS: 20-30
CFG: 1 (yes, ONE)
Settings for FLUX.2-klein-9B V1 (model for quick generations, but quality is still good)
SAMPLERS: er_sde, res_multistep, dpmpp_2m_sde, seeds_3
STEPS: 4 - 9
CFG: 1 - 1.4
img2img workflow: click here
Previous Models:
VintageBeauties ZIT (based on Z_Image_Turbo_bf16)
Sampler/scheduler combos to try:
dpm2_ancestral / sigmoid_offset (great contrast and shadows, depth, artistic)
er_sde / ddim_uniform (gives analog look to photo without LORAs)
lcm_custom_noise / linear_quadratic (gives that special render'ish SD 1.5 artificial look)
Krea:
Play around with the Guidance values between 1 and 13 — though going as high as 20 also works. Weird, but true.
Recommended settings:
Sampler:
dpmpp_2mScheduler:
betaSteps: 30
CFG (starting point): 5
Flux:
(v1 and v2) use at least 4.5 STR.
P.S. Use STR 3.5 for comfy backend in swarmui - thanks @snotty for the tip!
Description
Amazing detail, 20-30 steps, fullHD
FAQ
Comments (8)
Amazing model! Do you have any plans on doing a pruned version for ZIT?
Thanks! Nope, no plans (Flux2Klein9b is my fav atm), but you can use this LoRA with your fav pruned model for generally similar results: https://civitai.com/models/940109?modelVersionId=2455704
Generates beautifully at 8 steps with Euler. I'm able to get the native 1920x1080 nicely too.
Though it seems like the hands like to generate kinda huge? I'll be posting my examples in a bit, using your egyptian concubine prompt and workflow. Also tends to add extra fingers/melt the clothes into the body.
Civitai auto-flags 99% of realistic gens, and i really can't be bothered to touch it so if most to all of them don't appear, apologies. This site just stinks.
The fusion problem is just the original model's issue. Try changing the seed or doing a second img2img pass. I don't recommend using Euler.
yes use samplers I recommended, esp for v2 there's exceptionally good one. when posting images on civitai make sure you fill prompt field, also check boxes in TOOLS and TECHNIQUES. ah btw there's also "correct anatomy" LoRA for occasional fuse/anatomy problem but I forgot the name - it's here on civitai if you take a look.
what is the diff between analog and ne version of ZIT? is analog an updated ne or both are separate and exclusive versions?
Yes, the analog version is an updated ‘ne’ - it has a bit more detail and a more analog-ish feel. If you’re happy with ne outputs and don’t really need that natural/photo-realistic look, you can just stay with ne.
There are no workflows in your pictures.

















