■This is an experimental ground for Anima LoRAs.The LoRAs I create serve more of a role in stylistic tuning rather than reinforcing single concepts.There is no inherent superiority among the LoRAs; they simply serve different purposes. You can find the description for each LoRA in its respective tab.■If you notice pixel patterns in your generated images, try the VAE below. It removes the pixelation typical of the qwen_vae and makes the images much sharper.<a target="_blank" rel="ugc" href="https://civarchive.com/models/2718533/hdr-vae-anima-qwen-image">https://civarchive.com/models/2718533/hdr-vae-anima-qwen-image</a>■If the VAE looks a bit too saturated for your taste, try using this VAE merge node to blend it with the original qwen_vae to dial it in. A 0.5 merge should be just right.<a target="_blank" rel="ugc" href="https://civarchive.com/models/2487550/vae-merger-for-comfyui-anima">https://civarchive.com/models/2487550/vae-merger-for-comfyui-anima</a>■I would like to share the possibilities of anima with everyone.My wish is for many people to discover basemodels with potential and to see their possibilities unfold even further. I would be happy if I can help make that happen.■The anima architecture has been heavily modified and retrained from scratch—almost like a radical overhaul—but the base architecture is Cosmos-Predict2-2B. To put it simply, you could compare it to a lightweight version of Flux 1.I think it’s a great architecture capable of generating high-quality images despite its small size.I have a very good impression of Anima when it comes to color vibrancy, lighting, and prompt adherence.Its knowledge regarding NSFW concepts, characters, and styles is at least on par with SDXL. The overall feel of using it is also quite similar to SDXL.Furthermore, it is lightweight and easy to train. I believe large-scale training is also a viable option.Since we are provided with a base model that already contains a vast amount of knowledge, we rarely need to teach the model completely unknown concepts from scratch.Basically, our work mostly comes down to adjusting styles or reinforcing minor concepts and characters. You can achieve great results without having to do any heavy lifting.The developer has also ensured transparency by sharing the training settings, which means you are less likely to stumble over black-box issues.Because of this, the burden of training is low, making it an option well worth nurturing together as a community.■The LoRA has a stronger influence when used with shorter prompts.Since longer prompts often carry their own inherent style, the LoRA will primarily take on a supporting role to refine and unify the overall image.■<a target="_blank" rel="ugc" href="https://github.com/gazingstars123/Anima-Standalone-Trainer">https://github.com/gazingstars123/Anima-Standalone-Trainer</a>This is a great tool that allows for easy training, even on Windows. It has everything you need for LoRA training.Even if you run into any issues, you should be able to get your LoRA training up and running by troubleshooting with ChatGPT or Gemini.If you find the tool useful, you might want to consider making a donation to him. It allows the developer to focus more on development and deliver even better tools, which ultimately benefits you in the long run.■If you have any questions, please feel free to ask!日本語での質問も大丈夫ですのでご気軽にお声がけください～If you enjoy my work and feel like making a donation, I would be incredibly grateful. Even the smallest token of support goes a long way in helping me lighten the load.Whether I receive donations or not, I will keep doing what I love and pursuing my interests just as I always have. However, simply knowing that this kind of support exists brings me immense joy and serves as a huge driving force for me.<a target="_blank" rel="ugc" href="https://ko-fi.com/meg481074">https://ko-fi.com/meg481074</a>

anima_lora_lab

■This is a style and character LoRA for Fate/kaleid liner Prisma Illya.It was trained on a carefully curated dataset of approximately 5,250 images.■This LoRA was trained with a primary focus on character accuracy rather than just the art style. Because of this, you might find the baked-in style to be a bit too strong at times. If your goal isn't specific character reproduction, applying the LoRA at a lower weight/strength might be just right.Alternatively, I have included some backup LoRAs with lower training steps, so feel free to experiment and find the perfect balance for your needs.Not using quality tags (masterpiece, best quality etc...) actually allows the LoRA's style to show through more strongly, giving it more of a TV series vibe. Feel free to adjust this based on your preference.■Please refer to the bottom of the page for the list of trained character names.Note: I highly recommend prompting the character's physical traits alongside their character tag from the booru tag list. I did not prune (remove) general descriptive tags during training, so the character's features are not entirely forced into a single trigger word.A good trick is to run a reference image of the character you want to generate through a tool like WD14-tagger to get the necessary prompt tags.■Generating multiple characters at once can be hit or miss. You may need to reroll a few times or craft your prompts very carefully.■To be honest, since base models already have a good understanding of the main characters and famous Fate characters, you might not even need this LoRA for them. However, the side characters from Prisma Illya aren't well recognized by base models, so this LoRA will be a huge help when generating them.■Please keep in mind that not every character on the list will have perfect accuracy. Characters with very little screen time naturally have lower reproduction quality. For those specific characters, it would be better to train or use dedicated, individual character LoRAs.■For characters that aren't well-known or lack official names, I've assigned tags based on my own judgment. If you come across any characters you can't identify, please feel free to ask!■character list (trigger word) ■:::mainillyasviel von einzbernmiyu edelfeltchloe von einzbern ■:::sub(Family and schoolmates)katsura mimikurihara suzukamoriyama nanakigakumazawa tatsukosella \(fate\)leysritt \(fate\)irisviel von einzbernemiya shirou■:::sub2tohsaka rinluviagelita edelfeltbazett fraga mcremitzaugustecaren hortensiafujimura taiga■:::sub3tanakachild gilgamesh \(fate\)■:::sub4matou shinjimatou sakuraryuudou isseiiKotomine Kirei■:::sub5 (schoolmate Family)Kurihara Hibarimoriyama nanami■:::sub6beatrice flowerchildangelica ainswortherica ainswortherica ainsworth \(licht\)julian ainsworth

Files with SHA256: 994ac950a6297726c3e70e7d67ca6ef025a462f9991966e1c8becd3806a1fd98