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 of a person wearing an outfit similar to that of Supergirl in the CW TV show - specifically season 1.Please see "Further usage notes" further down below for some important notes regarding using this model!<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>'wearing spcc costume with cape'</li></ul><hr />Further usage notesThere are unfortunately some consistency issues with this model. Colors will often be wrong (usually a blue skirt instead of red), or small details wrong (especially the symbol). This is unfortunately an inherent issue with SD and not something I can fix through finetuning (I tried). It seems that SD just sees this outfit as being a Supergirl outfit no matter what tokens I use and as such inherits the same consistency issues the base SDXL Supergirl outfit exhibits.Generally these issues seem to be fixed to a seed however, so just generate until you have a good seed where the outfit has 100% likeness. That one should then work for most prompts.Also there are some issues with the style flexibility, where the outfit exhibits more consistency issues than usual the further away the style is from a photo (e.g. anime screencap). Again, not something I can fix.Generally this model is best used for photos of women, but with some patience can also be used with men or other styles.<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 />Changelogv1.0<ul><li>Initial release</li></ul>

Files with SHA256: d2f685b08a6d572ed3b18cb35e3c7ef3e767444831b2e048b5a155797d1873d4