Check out my new in-depth up-to-date training guide <a target="_blank" rel="ugc" href="https://civarchive.com/articles/3026/create-perfect-100mb-sdxl-models-for-all-concepts-using-48gb-vram-with-vastai-gpu-rental-guide">here</a>!<hr />DisclaimerFinancial support is very much appreciated, but please do so by donating to my <a target="_blank" rel="ugc" href="https://ko-fi.com/aicharacters">Ko-Fi</a> instead of sending me Buzz, as I currently have no uses for CivitAI Buzz!<hr />DescriptionAn SDXL 1.0 LoRa made by <a target="_blank" rel="ugc" href="https://civarchive.com/user/AI_Characters">AI_Characters</a> for producing images with the likeness of Emma Watson.I felt that base SDXL's version of Emma Watson is too overtrained (you can especially see it around the darkened eyes), so I produced my own version of her, and I feel this version has better flexibility than the other Emma Watson models.<hr />Recommended generation parametersWeight: 1.0 (adjust down as needed when used in conjunction with other LoRa's)Model: <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">SDXL 1.0 with 0.9 vae</a>Steps/Sampler/CFG/Resolution: 25 steps | DPM++ 2M Karras | CFG 7 | 1536x1536/1920x1080/1080x1920'Kohya Deep Shrink' settings: 4 blocks | 2 downscale | 0 start | 0.35 end | skip = true'CLIPTextEncodeSDXL' ComfyUI node resolution: 4096x4096Positive prompt: high-definition 8kNegative prompt: text, blur, low-resolution, low-quality, grainy, glossy, poorly drawn, amateur, poorly shot, compression artifactsUse "photo, realistic, render" in the negative prompt if prompting the outfit in a different style other than a photo.<hr />Trigger words (must be included in the prompt for the LoRa to take effect!)<ul><li>'femme ewpp'</li></ul><hr />Further usage notes/<hr />Usage permissionsYou may not sell this model, merges containing it, or images generated with it.Credit me when using this model in a merge or hosting it on a generation service.<hr />Changelogv1.2 'Skynet'<ul><li>new training config leading to less overtraining, more flexibility and diversity</li><li>naming each version from now on after the training config used</li><li>for more info see my training guide linked at the top</li></ul>v1.1<ul><li>simply switched the token from "ewpp woman" to "femme ewpp", leading to massively better likeness and flexibility</li></ul>v1.0<ul><li>Initial release</li></ul>

Files with SHA256: ec4ef50e3850182b4cf15d360d0c2ad918fa3791fc74ba325d9d1bfd384f611f