Lain_MiniMax.safetensors

148 MB · SafeTensor · bf16

Requires membership

<lain-iwakura-h3>

Lain Iwakura from Serial Experiments Lain, the best anime of all time in many regards. I never asked any buzz fee for ANYTHING I released on civitai, but this actually cost me money on runpod to train these LoRas (along with time obviously). So if you want to reward me just post something you created, that will make me happier than money or buzz ! ''^_^y' 08/08/2026 MINIMAX H3 : All hail the Lain MiniMax lora ! Brings out amazing video, very canonical. Though I had some good results with text2video I recommend using a quality reference pic or character sheet (ref2v), or a first frame pic (fl2v), to further enhance the likeliness of your video. If you're using a starting frame pic, as I found out also with other Loras, it's critical that the likeness of the character is the best possible, otherwise the LoRa will more or less catch up but it won't be the max quality as the model will also try to keep consistency with that first frame. Might be obvious, but since Minimax is new, just my 2 cents. 12/11/2025 QWEN : I finally got the nerves to do my V3 dataset because I wanted badly to have anime Lain on Qwen. The dataset is approx 150 faces directly from the anime plus supporting pics for the school outfit, bear costume and green cyberspace background/blue static noise. It works very well but sometimes seems to have minor line artefacts/glitches. I think they won't come out if you prompt stuff like "Professional anime" / "CGI anime" / "2.5D anime" and/or use negative prompting such as "artifacts, low quality, etc" It's able to do the really 90s canonic style of the anime as well as really modern yet very accurate IT WORKS VERY WELL WITH QWEN EDIT 2509 and if you bring in an anime Lain screenshot as a reference picture, the quality becomes EXCEPTIONAL I intend to do later another Lora to extend this one with a lot of outfits and accessories. We'll see ! Meanwhile, have fun. Let's all love Lain ''^_^y' NB : Special credits to for essential support and teamwork with this LoRa. Make sure to check her great Pony/Illustrious LoRas, which are just the finest a Serial Experiments Lain fan can download. OLD comments below about V2 : This one took 12 hours of training with 17250 steps and a 575 pics dataset (courtesy of Lain32_ which gets all the credit for carefully getting and selecting pictures from the anime, and making the awesome Pony version) Trigger word : Lain Iwakura This was not expected but this model is very good at making semi-realistic or even realistic pictures of Lain. I don't know yet exactly how to prompt them successfully, but you can have a look at my examples to see it can be done. Using a LLM such as chatGPT is essential to get the most out of this Lora (as for any flux generation really). Samples generated using Acorn's is spinning flux checkpoint but I haven't tried ressources more fine-tuned for anime.

SHA256

7A0A0B931807CDFA076C9EA77692210316299C660A48C14C4A2F341828126195

ModelTrends.ai Model ID

#26696

Steps

20

Seed

1303066158

Size

1280x704

Weight used

1