Update 10.07.2026. Lustify V10 (Krea 2) IS OUT! <a rel="ugc" href="https://civarchive.com/models/2503119/lustify-workflows-krea-2-sdxl?modelVersionId=3123550">Recommended workflow</a>.🚨 Attention: There was a bug with the fp8 version (the main download file) caused by a faulty fp16-to-fp8 conversion script, which resulted in blurry images lacking detail. If you encountered this issue, please re-download the file. It's now fixed. Sorry for the inconvenience!<h3 id="alternative-access-and-support:-outside-of-civitai's-early-access-you-can-get-the-model-via-my-boosty.as-always-after-the-early-access-ends-there-will-be-a-2-week-period-where-the-model-is-available-for-&quot;on-site-generation-only.&quot;-after-that-it-will-become-available-for-everyone-to-download.-the-open-release-date:-10082026-(10th-of-august).alternatively-you-can-make-a-direct-bitcoin-(btc)-donation-just-make-sure-to-dm-me-after-that:-1comzvrxtrxbz7bczdvxifsjhqhaf1yuzs">Alternative Access &amp; Support: Outside of CivitAI's Early Access, you can get the model via my <a target="_blank" rel="ugc" href="https://boosty.to/coyotte">Boosty</a>. As always, after the early access ends, there will be a 2-week period where the model is available for "on-site generation only." After that, it will become available for everyone to download. The open release date: 10/08/2026 (10th of August). Alternatively, you can make a direct Bitcoin (BTC) donation, just make sure to DM me after that: <code>1CoMZvrXtRXbz7BCzdvxifSjHqhaf1yUZs</code></h3><h3 id="lustify">LUSTIFY</h3>Lustify is a photoreal checkpoint optimized for creating high-quality imagery of women in explicit/sexual scenarios. The model has been trained on a hybrid dataset, meaning it natively understands both Danbooru tags and natural language prompting.Note: While it has a strong NSFW bias, if you guide it properly, it is fully capable of generating stunning SFW photography, objects, animals, and fantasy environments.<h3></h3><h3 id="crucial-points-before-you-download:">Crucial Points Before You Download:</h3><ol><li>NOT Pony or Illustrious-Based: This is a standard SDXL checkpoint. Do not use Pony/Illustrious LoRAs with it; they will not work correctly.</li><li>Distant Shots &amp; Anatomy Limitations: Like 99% of SDXL models, distant shots can sometimes suffer from distorted faces or hands. This is an inherent limitation of the base technology (4 channel VAE), not the finetune. It is incredibly easy to fix using Inpainting or ADetailer. Please utilize these tools rather than reporting this as a bug.</li><li>Experimental Nature: My training workflow involves a lot of unconventional, high-risk experimentation. Because of this, some prompt combinations that worked perfectly on other checkpoints might behave differently here. If you encounter unexpected behavior, feel free to give feedback so I can look into it.</li></ol> Recomended parameters: Sampler: DPM++ 2M SDE/DPM++ 3M SDE, Scheduler: Exponential/Karras Steps: 30 Cfg: 2.5-4.5. Highres.fix: upscale by 1.4-1.5, denoising ~0.4 For the distant shots of people you probably wanna use highres.fix and/or adetailer.Also, use reasonable positive/negative prompts, shizoprompting does more harm than good (with any SDXL model). Some tags that have a big visual impact with this model:<ol><li>Camera type tags: "shot on Polaroid SX-70", "shot on Kodak Funsaver", "shot on GoPro Hero", "shot on Canon EOS 5D", "shot on Leica T".</li><li>Photography styles: "analog photo", "glamour photography", "street fashion photography", "candid photo", "amateur photo".</li><li>Lighting types: "cinematic lighting", "neon lighting", "soft lighting", "dramatic lighting", "low key lighting", "bright flash photography", "warm golden hour lighting", "radiant god rays".</li><li>Film types: "Ilford HP5 Plus", "Lomochrome color film", "Fujicolor Pro".</li><li>Photographers: Alessio Albi, Martin Schoeller, Miles Aldridge, Oleg Oprisco, Tim Walker.</li><li>Others: "film grain", "bokeh", "dreamy haze", "technicolor", "underexposed", "low quality", "lowres"</li></ol>Alternatively, you can give a read to <a target="_blank" rel="ugc" href="https://civarchive.com/models/118213/creating-photorealistic-images-with-ai-using-stable-diffusion">this </a>wonderful prompting guide by <a target="_blank" rel="ugc" href="https://civarchive.com/user/PromptGeek">PromptGeek</a>. It has A LOT of useful tips I didn't know about even after years of using SD.

LUSTIFY! [NSFW checkpoint]

Available Model Variants:<ul><li>Raw: <code>fp16</code> / <code>fp8</code> / <code>int8_convrot</code></li><li>Turbo: <code>fp16</code> / <code>fp8</code> / <code>int8_convrot</code> / <code>Q4 GGUF</code> / <code>Q2 GGUF (my custom implementation)</code></li></ul>Hardware Recommendations:<ul><li>4 GB VRAM: Either Q2 or Q4 GGUF variant.</li><li>8 GB VRAM: Your best bet is the Turbo Q4 GGUF variant.</li><li>12 GB VRAM (or if you don't mind slightly longer generation times): Go with either Turbo int8_convrot (after the latest Comfy optimizations this is the preferred variant) or Turbo fp8.</li><li>24 GB VRAM: You can comfortably run the full Turbo fp16 variant.</li></ul>Use Turbo for everyday inference (generation) and Raw if you plan on training or fine-tuning.

Files with SHA256: 94d92700fc45200ef053895ec5655d4f64a69b924c1efaa457521dfc22bd5e00