<ul><li>Current version: v2.0</li><li>Recommended weight: 0.8-1.0 (the more LoRa's are chained together the lower this needs to be)</li><li>Recommended VAE: SDXL 0.9</li><li>Recommended model: SDXL 1.0</li><li>Recommended inference settings: See example images</li></ul>I recommend using the official SDXL 1.0 model that has the SDXL 0.9 VAE already integrated, which you can find <a target="_blank" rel="ugc" href="https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/sd_xl_base_1.0_0.9vae.safetensors">here</a>.Trigger words<ul><li>gh artstyle</li></ul>Changelogv2.0<ul><li>Somewhat improved likeness</li></ul><ul><li>Massively improved compatibility when used in conjunction with other LoRa's</li><li>Increased file size</li></ul>v1.0<ul><li>Initial release</li></ul>DescriptionGhibli artstyle LoHa for SDXL 1.0 trained (not merged) by me (AI_Characters). Credit is not mandatory but I would still appreciate credit when posting images using this LoHa on social media! Feel free to @ my Twitter and/or Instagram accounts too (@ai_characters)! I would love to know when it is used!If you want to support what I am doing, donations to my <a target="_blank" rel="ugc" href="https://ko-fi.com/aicharacters">Ko-Fi</a> would be greatly appreciated! Those will go towards funding the renting of GPUs for further experimentation and model making.Feel free to also try out my RVC2 AI voice models which you can find <a target="_blank" rel="ugc" href="https://huggingface.co/ai-characters/AI-Voice-Models-by-AI_Characters">here</a>!StatsDataset:<ul><li>132 images (screencaps)</li></ul>Training:<ul><li>rented RTX A4090 on <a target="_blank" rel="ugc" href="http://Vast.ai">Vast.ai</a></li><li>Training time: ~1h 30min</li><li><a target="_blank" rel="ugc" href="https://www.dropbox.com/scl/fi/8ha9w6g6kmohpdugqmyzs/example_v3-SDXL-LoHa-training-config-by-AI_Characters.json?rlkey=y96co84d9o6mj6th97e4ws86j&amp;dl=1">Example training configuration (v3)</a></li></ul>

Ghibli Artstyle LoHa (SDXL)

<ul><li>Recommended weight: 0.8-1.0 (the more LoRa's are chained together the lower this needs to be)</li><li>Recommended VAE: SDXL 0.9</li><li>Recommended model: SDXL 1.0</li><li>Recommended inference settings: See example images</li></ul>I recommend using the official SDXL 1.0 model that has the SDXL 0.9 VAE already integrated, which you can find <a target="_blank" rel="ugc" href="https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/sd_xl_base_1.0_0.9vae.safetensors">here</a>.Trigger words<ul><li>gh artstyle</li></ul>Changelogv2.0<ul><li>Somewhat improved likeness</li></ul><ul><li>Massively improved compatibility when used in conjunction with other LoRa's</li><li>Increased file size</li></ul>v1.0<ul><li>Initial release</li></ul>DescriptionGhibli artstyle LoHa for SDXL 1.0 trained (not merged) by me (AI_Characters). Credit is not mandatory but I would still appreciate credit when posting images using this LoHa on social media! Feel free to @ my Twitter and/or Instagram accounts too (@ai_characters)! I would love to know when it is used!If you want to support what I am doing, donations to my <a target="_blank" rel="ugc" href="https://ko-fi.com/aicharacters">Ko-Fi</a> would be greatly appreciated! Those will go towards funding the renting of GPUs for further experimentation and model making.Feel free to also try out my RVC2 AI voice models which you can find <a target="_blank" rel="ugc" href="https://huggingface.co/ai-characters/AI-Voice-Models-by-AI_Characters">here</a>!StatsDataset:<ul><li>132 images (screencaps)</li></ul>Training:<ul><li>rented RTX A4090 on <a target="_blank" rel="ugc" href="http://Vast.ai">Vast.ai</a></li><li>Training time: ~1h 30min</li><li><a target="_blank" rel="ugc" href="https://www.dropbox.com/scl/fi/8ha9w6g6kmohpdugqmyzs/example_v3-SDXL-LoHa-training-config-by-AI_Characters.json?rlkey=y96co84d9o6mj6th97e4ws86j&amp;dl=1">Example training configuration (v3)</a></li></ul>

Files with SHA256: 7415b9ac2caee61518afc9b2e62690f0f517d3db24e2abb51f012d18a91cd67e