Stable Diffusion · LoRA
Studio Ghibli Redmond V2 LoRA for SDXL
LoRA for SDXL that generates Studio Ghibli-style illustrations with trigger words Studio Ghibli and StdGBRedmAF. Trained on SDXL 1.0 base model.
About this model
StudioGhibli.Redmond V2 is a LoRA (Low-Rank Adaptation) for Stable Diffusion XL 1.0 that produces images in the distinctive Studio Ghibli animation style. The model was trained on a large dataset with GPU compute sponsored by Redmond.AI.
The LoRA uses two trigger words: "Studio Ghibli" and "StdGBRedmAF". Both should be included in prompts to activate the style. Recommended negative prompt: "bad art, ugly, text, watermark, duplicated, deformed". The model works with standard SDXL sampling settings (DPM++ 2M Karras, 20-30 steps, CFG 5-7).
The author notes the LoRA has high capacity for generating coloring book style images in addition to full-color illustrations. It is a non-commercial, fan-made creation intended for entertainment purposes. Weights are distributed in SafeTensors format.
Available on Hugging Face (artificialguybr/StudioGhibli.Redmond-V2) and Civitai (model 210452). The Hugging Face version targets SDXL 1.0; the Civitai page lists a v2.1 variant for SD 2.1.
Example outputs
Learn more
Read the in-depth guide about Studio Ghibli Redmond V2 LoRA for SDXL
Project signals
- 327 Hugging Face downloads
- 525 Civitai downloads
- 41 Hugging Face likes
Topics
diffusers · text-to-image · stable-diffusion · lora · template:sd-lora · base_model:stabilityai/stable-diffusion-xl-base-1.0 · base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0