Trained using 768x1152 resolution with SD3.5L base model.TensorArt hosts this Lora in addition to free onsite generation with SD3.5 Large (300 SD3.5 Large images per day for new users , then 100 images per day) : <a target="_blank" rel="ugc" href="https://tensor.art/models/791213304967242613?source_id=njq1pFzjlEOwpPEpaXny-xcu">https://tensor.art/models/791213304967242613?source_id=njq1pFzjlEOwpPEpaXny-xcu</a>//-----//Training methodYou can find the training images + captions here: <a target="_blank" rel="ugc" href="https://huggingface.co/datasets/codeShare/lora-training-data">https://huggingface.co/datasets/codeShare/lora-training-data</a> .A total of 93 images were used, 10 epochs over 9300 steps.The prompts were created in JoyCaption:HF spaces : <a target="_blank" rel="ugc" href="https://huggingface.co/spaces/fancyfeast/joy-caption-pre-alpha">Joy Caption Pre Alpha - a Hugging Face Space by fancyfeast</a>Joycaption Notebook : <a target="_blank" rel="ugc" href="https://colab.research.google.com/github/camenduru/joy-caption-jupyter/blob/main/joy_caption_jupyter.ipynb">https://colab.research.google.com/github/camenduru/joy-caption-jupyter/blob/main/joy_caption_jupyter.ipynb</a>and the trigger word 'nihei' was inserted into the resulting prompts at random places.//----//How to use:LoRa looks great in monochrome manga style , but will struggle for other formats.Themes in LoRA training image prompts: 'monochrome digital art illustration black-and-white drawing manga and anime styles, slender androgynous science-fiction form cybernetic humanoid surreal minimalist geometric woman female creature blades red futuristic tubes metallic organic mutated insect armor high-tech nightmarish helmet gun mechanical appearance urgency robotic tension fitting long hair contrasting gradient sharp weapon post-apocalyptic'

SD3.5L Nihei Tsutomu Blame! Style LoRa

Trained using 768x1152 resolution with SD3.5L base model.You can find the training images + captions here: <a target="_blank" rel="ugc" href="https://huggingface.co/datasets/codeShare/lora-training-data">https://huggingface.co/datasets/codeShare/lora-training-data</a>A total of 93 images were used. The prompts were created in JoyCaption: <a target="_blank" rel="ugc" href="https://colab.research.google.com/github/camenduru/joy-caption-jupyter/blob/main/joy_caption_jupyter.ipynb">https://colab.research.google.com/github/camenduru/joy-caption-jupyter/blob/main/joy_caption_jupyter.ipynb</a> and the trigger word 'nihei' was inserted into the resulting prompts at random places.LoRa looks great in monochrome manga style , but will struggle for other formats.Themes in LoRA training image prompts: 'monochrome digital art illustration black-and-white drawing manga and anime styles, slender androgynous science-fiction form cybernetic humanoid surreal minimalist geometric woman female creature blades red futuristic tubes metallic organic mutated insect armor high-tech nightmarish helmet gun mechanical appearance urgency robotic tension fitting long hair contrasting gradient sharp weapon post-apocalyptic'

nihei-for-SD35Large-v1.safetensors

v1.0

Trained using 768x1152 resolution with SD3.5L base model.You can find the training images + captions here: <a target="_blank" rel="noopener noreferrer nofollow" href="https://huggingface.co/datasets/codeShare/lora-training-data">https://huggingface.co/datasets/codeShare/lora-training-data</a>A total of 93 images were used. The prompts were created in JoyCaption: <a target="_blank" rel="ugc noopener noreferrer nofollow" href="https://colab.research.google.com/github/camenduru/joy-caption-jupyter/blob/main/joy_caption_jupyter.ipynb">https://colab.research.google.com/github/camenduru/joy-caption-jupyter/blob/main/joy_caption_jupyter.ipynb</a> and the trigger word 'nihei' was inserted into the resulting prompts at random places.LoRa looks great in monochrome manga style , but will struggle for other formats.Themes in LoRA training image prompts: 'monochrome digital art illustration black-and-white drawing manga and anime styles, slender androgynous science-fiction form cybernetic humanoid surreal minimalist geometric woman female creature blades red futuristic tubes metallic organic mutated insect armor high-tech nightmarish helmet gun mechanical appearance urgency robotic tension fitting long hair contrasting gradient sharp weapon post-apocalyptic'

Trained using 768x1152 resolution with SD3.5L base model. 
You can find the training data (93 images + captions) here: https://huggingface.co/datasets/codeShare/lora-training-data

LoRa looks great in monochrome manga style , but will struggle for other formats.

A total of 98 images were used. The prompts were created in JoyCaption: https://colab.research.google.com/github/camenduru/joy-caption-jupyter/blob/main/joy_caption_jupyter.ipynb  and the trigger word 'nihei' was inserted into the resulting prompts at random places.

Themes in LoRA training image prompts: 'monochrome digital art illustration black-and-white drawing manga and anime styles, slender androgynous science-fiction form  cybernetic humanoid surreal minimalist geometric woman female creature blades red futuristic tubes metallic organic mutated insect armor high-tech nightmarish helmet gun mechanical appearance urgency robotic tension fitting long hair contrasting gradient sharp weapon post-apocalyptic'


Files with SHA256: 3d983327d6e9b366202779a6a06594f2a44182419875019548d7da8313db3628