A versatile lightning model.(VAE is not baked in)Recommended VAE: sdxl_vae.safetensors<a target="_blank" rel="ugc" href="https://huggingface.co/madebyollin/sdxl-vae-fp16-fix/tree/main">https://huggingface.co/madebyollin/sdxl-vae-fp16-fix/tree/main</a>Basic positive prompthighly detailed, intricate texture, cinematic lighting, vibrant colorsBasic negative promptlow quality, monochrome, underexposed, low saturation, watermarkLoRA &gt; Offset<a target="_blank" rel="ugc" href="https://civarchive.com/models/137511/sdxl-offset-example-lora">https://civarchive.com/models/137511/sdxl-offset-example-lora</a>clip skip 2Recommended sampler: DPM++ SDE Karras / Euler ASampling steps: 4-6CFG: 1.5-2.5Resolution: 896x1152This model is for educational and non-commercial purposes, and not to cause harm, injury or violate laws.

LightningBloomXL

Version 2 brings general improvements in prompt coherence and leans more towards semirealism.Some prompt tricks below for using this model for realistic and anime images:Realism: analog film, photorealistic, Anime: anime, digital art(No need for negative prompts unless you specifically need them.) Recommended settings:Sampler: DPM++ SDE Karras // Euler A(Euler A has smoother touch, I'd suggest using it for realism)Sampling Steps: 4 - 6CFG 1.5 - 2.5Resolution: 896 x 1152 // 768 x 1024AfterDetailer for facial aesthetics. (not required for face portrait)Upscaling: optional

Files with SHA256: 7982d35ef94b408d72aab066e02ffdd11de3b8eb55355ba1c0358e827b3ec939