--Qwen2512
Trained with the best my technique. Best use with NiceGirls lora (if u need better female). Also works good with other loras + works good with some nsfw loras
--Qwen
I have prepared a version for Qwen. It looks quite promising; however, work on its enhancement is still ongoing. Examples with girls i generated with my lora NiceGirls
P.S: yeah, I changed epoch in models manager, cause 7k steps gave overtrained result, and in process of testing I understood that 3k is enough
🗺️ Backstory
Lately I kept getting DMs like “When will you drop an iPhone‑style LoRA?” Problem: iPhone LoRA already lives on Civitai—and, well, I shoot on Samsung. SamsungCam UltraReal captures the S‑series look you can’t fake with generic “phone” prompts
After some tests i noticed that the best to use with UltraReal Fine-tune or UltraReal Abliterated with 60 steps (yeah, so much steps gives pretty good details, also text usually looks much better).
Use 0.7-1.0 weight (depends on artifacts in scene)
🎨 What it brings
Vivid, high‑contrast colors
Smartphone softness – just enough in‑camera smoothing to feel “real phone,” not plastic CGI.
Highlight‑happy HDR – clipped whites around street lamps for that over‑exposed‑yet‑cinematic pop.
Less bokeh, more context
🤝 NSFWloras-friendly
Tested with NippleDiffusion and MysticXXX (For some reasons is not visible in Suggested Resources)
You can try to generate in 2MP for more realism and details, but be ready that in some scenes hands will be broken. But still looks very good imo in usual 1MP.
In most scenes removes blurred background (sometimes it could be still blurred). Also improves details a lot even on default flux.dev (cause mostly i train all loras for my ultrareal fine-tune checkpoint
P.S: yeah, first version is slightly overtrained, but i glad with a result. v2.0 already WIP
Description
FAQ
Comments (12)
That's awesome, looking forward to version 2511.
Just curious, what's the difference between 2511 and 2512? Cause I compared only 2509 and 2512
@Danrisi 2511 refers to the editing function,currently model editing and image generation in Qwen are separate functions.
@hanekawa0917792 okay, i'll take a look what can be done with 2511
@Danrisi you've worked hard, brother
could 2512 be loaded onto a 2511 workload anyway?
@snake88 No
Your work never fails to impress. Somehow you make these sloppy AI slop generators feel like there was an actual human being involved somewhere. Soulful work.
Very insane for him and team
Very insane brother. Hail for u and ur team
Good job! Could you make one for the base z-image, please?
Onlyfans Models Generator on home.
Download!!





