--- license: creativeml-openrail-m language: - en base_model: - stabilityai/stable-diffusion-xl-base-1.0 - nDimensional/NatVis-Natural-Vision-SDXL library_name: diffusers tags: - diffusers - safetensors - hyper-sd - hyper-sdxl - image-generation - SDXL - SDXLv1.0 ---
Natural Vision Hyper
Sample image Buy Me a Coffee at ko-fi.com --- ## Hyper Version(s) of [Natural Vision](https://huggingface.co/nDimensional/NatVis-Natural-Vision-SDXL) --- Model Info * Base Model - NaturalVision v1.0 + SDXL Lightning * VAE - sdxl-vae-fp16-fix * Type - Full-parameter fine-tune, FP16 * Medium - Photorealistic, Cinematography, Photography, Generalist * Hyper Generation Parameter Recommendations: * **Hyper with CFG:** * CFG: 6-8 * Steps: x for x in model_name_hyper_{x}steps. * Sampler: Euler * Schedule Type: SGM Uniform * **Hyper without CFG:** * CFG: 1 * Steps: x for x in model_name_hyper_{x}steps. * Sampler: Euler * Schedule Type: SGM Uniform * Recommended Generation Dimensions: * 1344x768 (16:9) — Cinematic Film Stills * 1536x640 (21:9) — Ultrawide Cinematic Film Stills * 1152x896 (4:3) — Fullscreen * 1216x832 (3:2) — Mobile landscape * 1024x1024 (1:1) — Square * 1024x704 (11:16) * 768x1344 (9:16) — Tall (Instagram stories / snapchat) * 896x1152 (3:4) * 832x1216 (2:3) — Mobile Portrait * 704x1024 (16:11) --- Latest Version: v2.7_8step_CFG
Hyper varients of NatViS versions priror to v2.7 will be uploaded over time.
Civitai Link: NSFW WARNING