Production-ready adult AI checkpoints
A checkpoint is the foundation model for a generation. Start here when you want to control the overall rendering style and capability, then layer compatible LoRAs on top. Filters distinguish image, editing, and video workflows so unsupported combinations never reach submission.
WAI-illustrious-SDXL
WAI-illustrious-SDXL is a Stable Diffusion model, primarily focused on generating characters, especially from popular social games and anime. It incorporates character data up to around May 2025 and includes an integrated VAE. The model benefits from using specific settings like Euler a sampler with CFG scale 5-7, and users should be mindful of prompt length to maximize image quality.
Z Image Turbo
Z-Image-Turbo is a highly efficient 6B parameter image generation model, a distilled version of Z-Image. It offers sub-second inference, excels in photorealistic image generation and bilingual text rendering, and demonstrates strong instruction adherence while operating efficiently on consumer devices. Other variants include Z-Image-Base for fine-tuning and Z-Image-Edit specialized for instruction-based image editing.
Flux.2 Klein
The FLUX.2 Klein models are fast image models that unify generation and editing. They offer state-of-the-art image quality with end-to-end inference, designed for real-time applications.
PornMaster-色情大师
PornMaster-色情大师 is a Stable Diffusion checkpoint model, with versions prior to v7 being based on the sd1.5 "Amateur Series". It allows for image generation under the Fair AI Public License, ensuring derivative works are also open source. The model creator offers customized LORAs and encourages users to support their work.
LUSTIFY! [SDXL NSFW checkpoint]
LUSTIFY! is a photorealistic SDXL checkpoint for generating images of women in sexual scenarios, trained to understand both danbooru tags and natural language prompts. It can also create SFW images if the NSFW bias is overcome. It is recommended to use specific samplers, schedulers, and CFG values for optimal results, and is not Pony or Illustrious based.
Smooth Mix Wan 2.2 (I2V/T2V 14B)
Smooth Mix Wan 2.2 (I2V/T2V 14B) is a versatile image and text-to-video model based on Wan 2.2 A14B. It generates high-quality images and smooth animations with variety in styles, and is uncensored to allow for NSFW content. While focused on generating female characters, it also responds to prompts like 'SmoothMixAnime' and 'SmoothMixRealism'.
Choose an adult AI checkpoint
Pick the workflow first
Text-to-image, image editing, and video workflows use different model capabilities. Use the media filter to narrow the list to validated support.
Compare model families
Base-model labels such as SDXL, Flux, or WAN describe the family a version belongs to and which LoRAs it can accept.
Confirm before spending
The generator validates the exact version and returns a server-authoritative credit quote before a job is submitted.