ICBINP | Civitai vs DreamShaper on CivitAI

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.

DreamShaper on CivitAI is a Stable Diffusion 1.x checkpoint by creator Lykon that targets illustration, portrait, and mixed-style image generation. Version 8 ships as a 1.99 GB fp16 SafeTensor download, with older builds, inpainting variants, diffusers exports, and an LCM distilled option listed on the model page. The checkpoint is free to download from CivitAI under the CreativeML Open RAIL-M license.

General-purpose SD checkpoints often lean either photoreal or anime. DreamShaper aims to handle portraits, backgrounds, and stylized characters in one weight file, which is why the author describes it as a Swiss-knife model for SD 1.5 workflows. The LCM build trades some quality for 5 to 15 step generations suited to video and real-time use.

Artists, hobbyists, and local Stable Diffusion users who want one base model before adding LoRAs are the main audience. CivitAI shows more than 1 million downloads and 18,000+ reviews on the listing, and Lykon notes suggested settings like CLIP skip 2 and high-res fix in the version notes. Paid CivitAI memberships are separate and fund on-site generation perks, not the checkpoint download itself.