A SDXL 1.0 LoRa made by AI_Characters for improving the photographic capabilities of the base SDXL 1.0 model. It makes the photos look more realistic, less fake and AI generated, and overall just higher quality - with slight improvements to NSFW as well.Usage recommendationsWeight: 1.0 (may need to be adjusted down when using 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>Generation parameters: 35 steps | DPM++ 2M Karras | CFG 7 Negative prompt: text, watermark, low-quality, signature, moiré pattern, downsampling, aliasing, distorted, blurry, glossy, blur, jpeg artifacts, compression artifacts, poorly drawn, low-resolution, bad, distortion, twisted, excessive, exaggerated pose, exaggerated limbs, grainy, symmetrical, duplicate, error, pattern, beginner, pixelated, fake, hyper, glitch, overexposed, high-contrast, bad-contrast with only the "G" text encoder enabled (see my article <a target="_blank" rel="ugc" href="https://civarchive.com/articles/2141">here</a> for how to do that)Trigger words<ul><li>"photo in phst artstyle"</li><li>"with beautiful lighting"</li></ul>Changelogv2.0<ul><li>Complete revision - trained with a much lower learning rate but more epochs, leading to increased likeness, flexibility, and variety; <s>fixed the eyes issue</s> that may have been a preemptive victory celebration - eyes are definitely better now but still a bit worse than base SDXL; slightly improved NSFW</li></ul>v1.0<ul><li>Initial release</li></ul>Additional InfoCredit is not mandatory but I would still appreciate credit when posting images using these LoRa's on social media! Feel free to @ my Twitter and/or Instagram accounts too (@ai_characters)! I would love to know when it is used!I share all of my model's and training knowledge for free, but donations to my <a target="_blank" rel="ugc" href="https://ko-fi.com/aicharacters">Ko-Fi</a> would be greatly appreciated! Testing so much and training so many model's costs a lot of money (and time).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>!See <a target="_blank" rel="ugc" href="https://civarchive.com/articles/1771">here</a> for an extensive article about my entire training workflow and configuration if you want to train your own SDXL 1.0 LoRa's and achieve results similar as me!Stats (v2.0)Dataset:<ul><li>311x photos</li></ul>Epoch chosen for the final model:<ul><li>35</li></ul>Learning rate:<ul><li>6e-6</li></ul>For more info - including the training configuration used - see the article linked at the end of the "Additional Info" section.

Files with SHA256: 35ba4a6fb350d899153da27ca398209df4ef151b9de198258718489f5c2be4fc