Aniimage-1

Aniimage-1 is the first latent diffusion model developed by 8BitStudio. The model is a 256x256 anime image generation model trained from scratch using a UNet + VAE + CLIP architecture. Aniimage-1 has been trained on 830,001 anime images from Danbooru. It is not based off of any existing models, the unet is trained from scratch.

Model Details

Resolution	256×256
Architecture	Latent Diffusion (UNet + VAE + CLIP)
Parameters	~400M
Training Steps	88,000
Batch Size	64
Dataset	~830K curated anime images from Danbooru
GPU	NVIDIA RTX 5060 Ti 16GB
Scheduler	DDIM or DPM ++ 2M

Requirements

• GPU: ~3.4 GB VRAM minimum (recommend 4+ GB)
• CPU: ~2 GB RAM. Image generation is extremely slow on cpu.

Quick Start

after downloading, install the dependencies.

pip install torch torchvision diffusers transformers safetensors pillow huggingface_hub
python generate_hf.py

recommended settings: Scheduler on DPM ++ 2M with 25 steps and a cfg of 7.5. recommended negative prompt: "low quality, ugly, blurry, distorted, deformed, bad anatomy, bad proportions, extra limbs, missing limbs, watermark, text, signature, washed out, flat colors, manga panel, disfigured, poorly drawn, jpeg artifacts, cropped, out of frame"

Prompting

Aniimage uses plain text captions meaning for the best result use plain english.

Do "A smiling anime girl with red hair and a school uniform" Not "1girl, solo, smile, red_hair, school_uniform, anime_coloring"

Capabilities

• Anime character generation with varied hair colors and styles
• School uniforms, fantasy outfits, maid dresses, and more
• Background scenes: cherry blossoms, night sky, interiors, nature

Limitations

• 256×256 resolution — fine details like hands and small features can be rough
• Faces can sometimes look similar or 'melty' across different prompts
• Complex multi-character scenes may have merging issues
• Little to none NSFW content — trained on mostly SFW dataset only
• Does worse when generating men due to dataset bias

What's Next

Aniimage-1.5 — a 512×512 fine-tune of this model is currently in development, which will significantly improve detail and clarity. Code for training may be released at some point on github

License

Apache 2.0