AI porn models for adult image and video generation
Browse the building blocks behind the factory. Filter checkpoints and LoRAs by image or video support, base model, and tags, then open any version directly in the unified generator.
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'.
How checkpoints and LoRAs fit together
Start with a checkpoint
A checkpoint controls the base rendering system. Its supported modes determine whether it can create images, edit an input, or produce video.
Match the base model
A LoRA must target the same base-model family as the checkpoint. Similar names do not guarantee compatible weights.
Check the validated workflows
A catalog version can be documented before it is generator-ready. Only versions with validated broker and artifact mappings can spend credits.