Unlimited Replicant

🚀 Unlimited Replicant Model Card

Unlimited Replicant is an AI art - specialized image - generation AI developed as an alternative to the leaked Novel AI Diffusion.

Title: Replicant from unlimited sky.

English version is here.

🚀 Quick Start

The model can be downloaded in safetensors format.

💻 Usage Examples

It's used in the same way as Stable Diffusion v2. There are many methods, and two patterns are provided: Web UI and Diffusers.

Basic Usage

Web UI

Similar to using Stable Diffusion v2, place the safetensor - formatted model file in the model folder. For detailed installation methods, refer to this article. It is recommended to install xformers and turn on the --xformers --disable - nan - check options. Otherwise, turn on the --no - half option.

Diffusers

Use 🤗's Diffusers library.

First, run the following script to install the library:

pip install --upgrade git+https://github.com/huggingface/diffusers.git transformers accelerate scipy

Then, run the following script to generate an image:

from diffusers import StableDiffusionPipeline, EulerAncestralDiscreteScheduler
import torch

model_id = "alfredplpl/unlimited-replicant"

scheduler = EulerAncestralDiscreteScheduler.from_pretrained(model_id, subfolder="scheduler")
pipe = StableDiffusionPipeline.from_pretrained(model_id, scheduler=scheduler, torch_dtype=torch.float16)
pipe = pipe.to("cuda")

prompt = "masterpiece, anime, close up, white short hair, red eyes, 1girl, solo, red roses"
negative_prompt="lowres , kanji,  monochrome, ((bad anatomy)), ((bad hands)), text, missing finger, extra digits, fewer digits, blurry, ((mutated hands and fingers)), (poorly drawn face), ((mutation)), ((deformed face)), (ugly), ((bad proportions)), ((extra limbs)), extra face, (double head), (extra head), ((extra feet)), monster, logo, cropped, jpeg, humpbacked, long body, long neck, ((jpeg artifacts)), ((censored)), ((bad aesthetic))"
images = pipe(prompt,negative_prompt=negative_prompt, num_inference_steps=30, height=1024, width=768).images
images[0].save("girl.png")

⚠️ Important Note

• Using xformers can speed up the process.
• If you have limited GPU memory when using a GPU, use pipe.enable_attention_slicing().

Advanced Usage

The model has various potential advanced usages, such as in research and development scenarios. For example, on Discord, you can perform prompt engineering, fine - tuning (like DreamBooth), merging with other models, and checking the model's independence from other non - Stable Diffusion models using checksum or hash functions.

📚 Documentation

Expected Use Cases

• Self - expression: Use this AI to convey your uniqueness.
• Reporting on image - generation AI: It's allowed not only for public broadcasters but also for for - profit enterprises. The right to know about image - synthesis AI is considered not to have a negative impact on the creative industry, and freedom of the press is respected.
• Research and development:
  • Use the model on Discord for prompt engineering, fine - tuning (such as DreamBooth), and merging with other models.
  • Examine the model's performance using metrics like FID.
  • Check the model's independence from non - Stable Diffusion models using checksum or hash functions.
• Education:
  • For graduation projects of art college students and vocational school students.
  • For graduation theses and assignment projects of university students.
  • For teachers to convey the current situation of image - generation AI.
• Illustrations and headers for blog articles: It's allowed even for paid articles as long as generating images is not the main purpose, as it's judged not to interfere with illustrators' work.
• Use cases described in Hugging Face's Community: Ask questions in Japanese or English.

Unexpected Use Cases

• Representing things as facts.
• Using it in monetized YouTube content.
• Directly providing it as a commercial service.
• Doing things that trouble teachers.
• Other actions that have a negative impact on the creative industry.

🚫 Prohibited or Malicious Use Cases

• Do not publish digital forgeries (Digital Forgery) as it may violate copyright laws.
• Do not perform Image - to - Image on others' works without permission, which may violate copyright laws.
• Do not distribute pornographic materials, which may violate Article 175 of the Criminal Code.
  • Avoid actions that do not follow the so - called industry etiquette.
• Do not claim non - factual things as facts, which may lead to the crime of interference with business by force.

✨ Features

Unlimited Replicant is an AI art - specialized image - generation AI developed as an alternative to the leaked Novel AI Diffusion. It can generate appropriate images according to prompts, using algorithms such as Latent Diffusion Model and OpenCLIP - ViT/H.

📄 License

The license is a dual - license. Based on the original CreativeML Open RAIL++ - M License, a prohibition on commercial use (except for exceptions) is added, and something similar to AGPL is also added. The reason for adding the prohibition on commercial use (except for exceptions) is the concern that it may have a negative impact on the creative industry. If you work for a for - profit company, please consult your company's legal department. If you use it for personal hobbies, you can use it while following general common sense.

If you want to use it commercially, please contact us separately at ozaki.yasunori@outlook.com.

🔧 Technical Details

Model Information

Training

Training Data: Data and models compliant with domestic laws.

Training Process:

• Hardware: A6000x2

Evaluation Results

Third - party evaluation is being sought.

Environmental Impact

• Hardware Type: A6000x2
• Usage Time (in hours): 1000
• Training Location: Japan

Legal Information

This model was created in Japan, so Japanese laws apply. The training of this model is claimed to be legal based on Article 30 - 4 of the Copyright Law. Also, regarding the distribution of this model, it is claimed that it does not fall under the category of principal offenders or abettors in light of the Copyright Law and Article 175 of the Criminal Code. For more details, refer to the opinion of lawyer Kakinuma.