Want to master photorealistic workflows or generate consistent characters using your own LoRA? Join my private Discord (via my Fanvue) for in-depth guides, prompt packs, and personal support from me. Check what's included: https://huslyo123.carrd.co/
HuslyoRealism XL [SDXL]
After tons of experimenting, merging, and testing, I am releasing my first full custom checkpoint:
HuslyoRealism XL: Photography-first realism checkpoint for SDXL, tuned for natural light, soft skin, and NSFW realism.
Enjoying the model? A green thumbs-up helps big time!
This is a photography-first model capable of both SFW and NSFW content, with a strong NSFW focus for people. I created 12 different versions of HuslyoRealism during development, generating over 2800 images per version to test stability and consistency. This release is the most balanced so far, though still experimental.
⚙️ Recommended Settings normal version
Sampler: DPM++ 2M SDE Karras or DPM++ SDE Karras
Steps: 30-32
Clip Skip: 2
CFG Scale: 4-6
Resolution: 768x1152, 648x1152, 864x1152, or any SDXL resolution you prefer.
Eyes/Face: Use FaceDetailer or Adetailer with face_yolov8n.pt and eye detailer with PitEyeDetailer-v2-seg.pt
Negative: cartoon, illustration, anime, painting, CGI, 3D render, low quality, watermark, logo, label, deformed eyes, deformed iris
Faces and eyes can be a bit hit or miss in this version, something I’ll address in V2. That said, I’ve posted hundreds of successful examples in the gallery, each with full prompt and settings included. Take a good look at those to see what works
⚙️ Recommended Settings dmd version
Sampler: LCM
Steps: 7
Schedule type: Karras
CFG Scale: 1
Resolution: SDXL friendly resolutions like 768x1152, 648x1152, 864x1152
Face handling: FaceDetailer or ADetailer with face_yolov8n.pt and an eye detailer like PitEyeDetailer v2
Negative prompt: cartoon, illustration, anime, painting, CGI, 3D render, low quality, watermark, logo, label, deformed eyes, deformed iris
📝 Model Notes
Great for both SFW and NSFW images, but also highly capable of scenery (landscape or portrait).
Mixed with my Touch of Realism LoRA and other LoRAs in this series, meaning you do not need to load those extra LoRAs (though you can use them to amplify effects).
Focus on smooth skin tones, natural lighting, and photography compositions.
Responds very well to film grain, grainy texture, photo of… prompts, and excels in macro photography-style close-ups.
Expect slightly softer faces compared to some other SDXL models, but with enhanced realism.
I will continue developing new versions. If this one does not meet your goals, I highly recommend switching to Analog Madness XL3 (my favorite general-use model) or Lustify (NSFW peak performer).
🔤 Prompt Suggestions & Keywords that Work Well
This model responds especially well to the following prompt fragments and styles. Combine them for best results:
• foreground blur, soft foreground, realistic depth falloff, cinematic shallow DOF, lens softness, bokeh in the distance
• natural light from the side, sunlight through the window, catching the sunlight, sun-kissed skin, golden hour light, dusty sunlight
• soft focus edges, ISO noise effect, grainy texture, realistic grain, soft skin texture with visible grain
• retro selfie style, analog photo look, vintage photo vibe, nostalgic atmosphere, faded look, vintage lighting, retro color grading
• natural textures, clay and wood tones, sunlit minimalist room, photorealistic beige mood, earthy palette, neutral styling, beige interior, Scandinavian light, calm aesthetic
• Works well with photo of [subject], macro shot of, close-up portrait of, and similar photography-based phrasing
Feel free to remix or combine them. The model was designed to reward photographic phrasing and natural-light descriptions.
📚 Credits & Merge Details
Models in this merge Lustify (one of the best NSFW SDXL models in my opinion), Juggernaut + a large variety of other models I use a lot (no credit required).
Custom LoRAs included directly in this model:
Touch of Macro (unpublished) (trained on my own macro photography)
Touch of Close-up (unpublished) (trained on my own studio photography)
Touch of Photography (unpublished) (trained on my own images)
Touch of Dreamlight (unpublished)
Touch of Realism V3 (unpublished)
Touch of Direct Flash (unpublished) (trained on my own studio flash photography)
3 Body Type Specific LoRAs (unpublished or my private Discord only)
This is an experimental merge. If it is not for you, that is fine, I can recommend: Lustify or Analog Madness.
✅ License / Usage
Free to use, merge etc. No credit required. If you post images somewhere, a shout-out is always appreciated, but not required.
📸 Prompt Transparency
All images in the gallery below come with full prompts, settings, and metadata. Feel free to recreate them exactly or use them as a starting point for your own generations.
In my private Discord (tied to my Fanvue sub), you’ll find photorealistic workflows, consistent character setups, A1111 and ComfyUI workflows, plus Wan2.2 video workflows (local and Runpod). Join my private Discord through Fanvue for in-depth guides, prompt packs, and personal support from me. Check what’s included: https://huslyo123.carrd.co/
Thanks for the amazing support and feedback, it really keeps the project moving forward!
Description
Enjoying the model? A green thumbs-up helps big time!
HuslyoRealismXL V2 is my attempt to improve hands, portraits, mid-body shots and feet in SDXL while keeping the realism I loved from V1. It turned out quite well, though it’s still experimental. I mixed a lot of my own LoRAs and images with the previous checkpoint to push the quality further. You’ll still 100% need ADetailer (A1111), FaceFix (CivitAI generator) or Facedetailer (ComfyUI) for eyes and preferably the face.
FAQ
Comments (7)
Holy smoke, what a checkpoint🥂❤️
Thanks! :-D
@Huslyo123 I use your touch of realism and grain, almost all the time, fantastic sets of loras you've created.
@6vidit9 Thanks a lot, appreciate it! Really cool to hear you’re using Touch of Realism and Grain that often. I’ll be uploading some fun new stuff soon and hopefully the next version of Touch of Realism as well. Great that you’re using Touch of Grain by the way, it’s such a fun one, but not many people have discovered it yet 😉
@Huslyo123 That's great to hear, mate! I'd love to check them out. I'm sure people will find out about the amazing things you create :)
Hello! Thank you for the update—I’m really looking forward to working with the new version!
Actually a legit top3 checkpoint. 💯
Rarely these days gets anymore surprised by checkpoints, since all feel rather "samey" (you all know what i mean), but this was a positive surprise and has many great qualities and after testing for half a day, instantly enjoy using it a lot.
Shares some great qualities from one of my favorite checkpoints done by @aramintastudio that has a some unique magic what comes to how well all my favorite Loras work, the general aesthetics, vibe and style.
This V2 is VERY good out of the box (with minimal to zero Loras) with lightings and atmospheres and photorealism, images look great without having to force them to be with your usual Lora Stack of Doom(tm). And because of that lighting and composition is already great, you can only just make it greater with your own prompting game, not having to "fight" to get good results, you get good results and amazing results. There is also a lot of variety and surprises. What happens rarely, or feels like that, with a lot of checkpoints that must have 80% shared same base, so results are the same.
So Huslyo been cooking this up with some real magic, love and care. I see instantly there are some vibes of your Touch of Loras and that is a good thing. Not overpowers the creative freedom, just adds some flavor and realism, especially to the lighting and backgrounds and that means getting amazing looking surfaces, reflections and atmospheres.
It's really good with prompts, understands my intentions (not an easy task, i have a silly adhd brain lmao) and results with what i wanted, and sometimes with what i needed but did not know i wanted that, but i did after seeing it. That is a perfect feeling to have while rendering a couple hundred images during the day, some fun surprises to a txt2img addict.
"Highest quality, masterpiece, professional aesthetic.." No, not writing a prompt, those describe this checkpoint. 💜
So big thanks for your work, would donate all my Buzz if was not out of them hih. ^^