ICBINP | Civitai vs Lexica

ICBINP is a Stable Diffusion 1.5 checkpoint merge built to push photorealistic image generation as far as a local SD 1.5 setup allows. The Civitai model page hosts multiple versions, with Mid 2024 as the latest major release updated in February 2025. Each variant ships as a pruned fp16 SafeTensor file with the SD-v2 840k VAE baked in, so you can load it in Automatic1111, ComfyUI, or any standard SD 1.5 interface without swapping VAEs.

Where most photorealistic checkpoints chase a single aesthetic, ICBINP grew through successive merges. It started from the RCNZ Gorilla With A Brick base, then folded in ten more photorealistic models at varying weights plus noise offset tuning. The Mid 2024 version adds a LoRA trained on Pexels stock photos merged with ICBINP Final, which tightens skin and lighting realism but still shows typical SD 1.5 quirks like cleft chin bias.

The author recommends DPM++ 3M SDE Karras or DPM++ 2M Karras at 20 to 30 steps with CFG between 2.5 and 5. Resolution sweet spot is 640x960 with a hires fix pass, though 768x1152 works if you hunt seeds to avoid duplicate heads. Beyond portraits, the checkpoint handles CGI characters and landscapes when prompted accordingly.

Downloads are free from Civitai under CreativeML Open RAIL-M. The Mid 2024 file (ICBINP_midYear.safetensors) weighs 2.21 GB and needs about 3.4 GB recommended VRAM. With 163,500+ downloads and 285 Very Positive reviews, it remains one of the most downloaded photorealistic SD 1.5 merges on the platform.

Lexica lets you search a massive gallery of AI-generated art, inspect the prompts behind each image, and create new visuals with its Lexica Aperture model. The Generate workspace defaults to 960 by 1440 output, and every prompt submission spends four image credits before results appear.

Unlike general chat tools that bolt on image buttons, Lexica built its reputation as a prompt search engine first. You can reverse-engineer styles from existing images, then move into Aperture generation with fast and slow queues, custom aspect ratios, and optional image uploads. Starter and Pro images stay public in search; only the Max plan keeps generations private by default.

Artists, designers, marketers, and hobbyists use Lexica to explore visual ideas and produce commercial-ready assets under plan-specific licenses. Paid plans are required to generate images because Lexica does not offer a free tier, though subscribers can buy extra fast generations at $0.05 each when monthly limits run out.