This is a place for experimenting with SD1.5 LoRA.The main goal is overall enhancement rather than focusing on a single concept.■Dora_nsfw_remember is intended to complement my test merge model, but since the training is done on NovelAI v1, they should work fine with its derivative models.my test model:<a target="_blank" rel="ugc" href="https://civarchive.com/models/1246353/sd15modellab"> https://civarchive.com/models/1246353/sd15modellab</a>■nai_v2_highres is a high-resolution stabilizing DoRA for novelai_v2.Please download the official checkpoint from the URL below.I’ve also made a safetensors version just in case.<a target="_blank" rel="ugc" href="https://huggingface.co/NovelAI/nai-anime-v2">https://huggingface.co/NovelAI/nai-anime-v2</a><a target="_blank" rel="ugc" href="https://civarchive.com/models/1772131">https://civarchive.com/models/1772131</a>■nai_v2_semi-real is a semi-realistic style DoRA for novelai_v2.■I use OneTrainer for training and ComfyUI for inference.■I will share my training settings and inference workflow as much as possible.■If the prompt is short, the background may become simple or the style may lean toward realism. By using the uploaded tipo_workflow, you can automatically generate longer prompts—so please give it a try!■Sometimes saturation occurs due to overfitting and the model’s compatibility. Adjusting DoRA , prompt weight strength, or reviewing the cfg can help improve this.■There’s also a high-resolution inference workflow using kohya_deep_shrink.It expands composition and removes the need for high_res_fix.1152px offers a good balance of quality, stability, and speed, while 1536px is more dynamic and detailed.By the way, this Dora was created to give SD1.5 a level of concept understanding comparable to my PixArt-Sigma anime fine-tune.SD1.5 with Dora applied will likely be the most compatible refiner—it's ideal for i2i tasks.my pixart-sigma finetune.<a target="_blank" rel="ugc" href="https://civarchive.com/models/505948/pixart-sigma-1024px512px-animetune">https://civarchive.com/models/505948/pixart-sigma-1024px512px-animetune</a>■Please feel free to ask if you have any questions!日本語での質問も大丈夫ですので気軽にお声がけください!

sd1.5_lora_lab

■We’ve trained with twice the number of steps as before. Judging from the sample images, the results look significantly improved. ■It works fine at strength 1, but if the style is too strong or unstable, try lowering it to 0.75or 0.5 for balance.■I’ll also share the OneTrainer training backup data—use it as a reference for your training settings.It’s also possible to resume training from this DoRA checkpoint.That said, I think training at 1536 resolution was excessive; 1280 px should be sufficient to keep high-res generation flexible.Also, if VRAM use isn’t much different, AdamW is preferable to AdamW 8-bit as the optimizer.

Files with SHA256: 9bea85f4771f3b78a67f10daab15d5f90b93eb163ec2ab4d2c0079db7f9458f0