---&gt; The sale or distribution or reposting of this Lora on other sites is prohibited. The character is © of the author who authorized me to create this Lora for Civitai and TA. The costume and character designs and backgrounds have © their respective creators and © for video novel. &lt;---Loras are trained with Kohya and screenshot from original video novel. ILLustrious SDXL version are refined for more realism. This model does not use any real-life or celebrity content. Please do not use this model for any real-life or celebrity.Illustrious Weight 0.5 - 0.8 (0.5 for more realism and fantasy with realistic checkpoints)<h3 id="i-use-this-generator-loras-for-backgrounds-for-my-characters-greater-ninjagirls-characters">I use this generator loras for backgrounds for my characters ---&gt; <a target="_blank" rel="ugc" href="https://civarchive.com/models/459720/ninja-girls-video-novel-hs2dx-to-ai-sd15-ill">Ninjagirls characters</a></h3>Recommended for a better result: vae-ft-mse-840000-ema-pruned, ADETAILER mediapipe face mesh.Setting : Sampling Euler-a or DPM Karras, HiresFix on, R-ESRGAN 4x+, Denoising 0.4, Upscale 2x, Sampling steps 35+, Resolution 512x768, Upscale 4x Ultra Sharp next passage.<hr /><h3 id="settings-for-illustrious-version:">Settings For Illustrious version:</h3>To achieve a realistic result, a <a target="_blank" rel="ugc" href="https://tensor.art/it-IT/models/869285461682562510/Illustrious-SDXL-Realistic-v1">realistic</a> ILLustrious non-merged checkpoint should be used. If you use merged models with anime models, the result may be very different from mine. Do not use corrective loras in addition to the main lora because they often only ruin the result. If possible, do not exceed 150 tokens in prompts. Too many words in prompts do not improve the result. The parameters I use are the following :Steps: 35, Sampler: Euler a, Schedule type: Automatic, CFG scale: 4.5, Size: 512x768, Denoising strength: 0.35Trigger words (use only one trigger at a time) :BKG 1 : realistic photo of gardenbkg1, outdoors, scenery, sunny dayBKG 2 : realistic photo of mansionbkg3, outdoors, scenery, sunny dayBKG 3 : realistic photo of villagebkg2, outdoors, scenery, sunny dayNegative prompt ILL : (low realism), low quality, (3d rendering, cgi)NOTE : For perfect results use max 100 token on positive and negative prompt and not use embeddings or other corrective loras. Put this lora at end of your prompt and start with weight 0.5. Lora character and her trigger go at the beginning of the prompt.Add to Positive prompt for ILL : (realistic:1.5), realistic skin details, 8k, ...... trigger words<hr />If you like the character, always leave a vote and if you give some buzz you will allow me to train other characters of this beautiful video-novel on Ninja girls.The series includes over 60 characters and scenary. Maybe I will publish other characters and scenary in the future if the voting of the characters will improve. If you want you can check other characters <a target="_blank" rel="ugc" href="https://tensorhub.art/it-IT/models/950590786028719323">here</a>. Thanks.

Files with SHA256: 4170c264494b98813b145fb1f1b654548630764be1efb0da57a739ab7f1f4dab