This LoRA model is a bit unique in that not only does it assist in imitating the Princess Connect! Re:Dive art style, but due to the relatively consistent composition and posing in the reference works it is very good at creating scenes with a centrally located character as the focus with high level of detail for and around the character.<h2>Main features</h2><ul><li>Good at wide aspect ratios</li><li>Good at keeping characters in frame ("feet out of frame", "thighs", etc. prompts won't cause super zoom in nearly as often)</li><li>Good at enhancing visual elements around the subject character</li><li>Priconne art style</li></ul><h3>Other features</h3><ul><li>Good for highres fix (all images bucket to 960x512, trained at 960 res)</li><li>A bit better than usual at background continuity across areas interrupted by foreground (just a little, don't expect miracles)</li><li>Helps somewhat with Counterfeit-V2.5 LoRA compatibility by reducing the multiple characters appearing issue.</li><li>Can assist with composing scenes for use with ControlNet, img2img to achieve detailed compositions of different styles</li></ul><h2>Use &amp; Prompting</h2><ul><li>No activation tokens are required.</li><li>(At the moment) For use with <a target="_blank" rel="ugc" href="https://civarchive.com/models/4468/counterfeit-v25">Counterfeit-V2.5</a>. I can't guarantee it'll work well on any other model, as LoRA trained on Counterfeit-V2.5 tend to behave oddly when used elsewhere.</li><li>Weights between 0.6-1.0 recommended.<ul><li>If using with character LoRA, try starting on the lower end</li><li>Other style LoRAs will tend to clash. I recommend low or no weight of the accompanying LoRA for initial gen and then img2img afterwards</li></ul></li><li>Sometimes, faces will appear on the right side (due to ☆6 Rima...). Add (solo) or other such emphasis/negatives to suppress this.</li></ul><h2>Dataset</h2>All ☆3 and ☆6 character art up to Café Tamaki. Six star artworks were repeated 4x per epoch, three star 1x per.Tagging was done via wd14-swinv2-v2 with threshold 0.15. All character tags were then removed.

Princess Connect - Priconne Character Focus ☆3/☆6 Style

Trained on Counterfeit-V2.5_pruned.Example imagesGenerated using Counterfeit-V2.5_pruned. When used alone weight 0.9-1.0 was used. When used with character LoRA weight 0.6 was used. All images were processed with txt2img + highres fix. For the Ichiso-style image, after initial generation, img2img Ultimate SD Upscale was used to restyle the image using only the target style LoRA.Training Parametersss_clip_skip: "2"ss_color_aug: "False"ss_dataset_dirs: "{"1_threestar": {"n_repeats": 1, "img_count": 223}, "4_sixstar": {"n_repeats": 4, "img_count": 52}}"ss_epoch: "60"ss_flip_aug: "False"ss_full_fp16: "False"ss_gradient_accumulation_steps: "1"ss_keep_tokens: "1"ss_learning_rate: "0.0001"ss_lr_scheduler: "cosine_with_restarts"ss_max_bucket_reso: "960"ss_max_token_length: "150"ss_mixed_precision: "fp16"ss_network_alpha: "128.0"ss_network_dim: "128"ss_new_sd_model_hash: "a074b8864e31b8681e40db3dfde0005df7b5309fd2a2f592a2caee59e4591cae"ss_num_reg_images: "0"ss_random_crop: "False"ss_resolution: "(960, 960)"ss_sd_model_name: "Counterfeit-V2.5_pruned.safetensors"ss_shuffle_caption: "True"ss_text_encoder_lr: "1e-05"ss_total_batch_size: "2"ss_unet_lr: "0.0001"

Files with SHA256: e7777b5223ba8a319b6cce4401bd612b0643c5de81e2ce2474f5e350a269fa0f