| --- |
| language: |
| - en |
| license: mit |
| pipeline_tag: text-to-image |
| tags: |
| - anime |
| - diffusion |
| - text-to-image |
| - pytorch |
| - latent-diffusion |
| - ddim |
| - classifier-free-guidance |
| --- |
| |
| # AnimeGen - Lightweight Latent Diffusion Text-to-Image Model |
|
|
| Compact text-to-image model trained from scratch on **65,675** real anime images with Danbooru tags. Uses **latent diffusion** + **DDIM** + **classifier-free guidance (CFG)**. |
|
|
| ## Architecture |
| 1. **Autoencoder** - 96x96 -> 64-channel latent. Reconstruction **PSNR 27.8 dB**. |
| 2. **GRU tag encoder** - comma-separated Danbooru tags -> conditioning vector. |
| 3. **Conditional Latent Diffusion U-Net** (base=256) + **CFG** at sampling. |
|
|
| ## Key Metrics |
| - Trained on **65,675 unique** anime images (96x96) |
| - AE reconstruction: **PSNR 27.8 dB** |
| - **Classifier-free guidance** (cfg=4.0) at sampling |
| - **Latent normalization** (per-channel mean/std) prevents out-of-distribution latents |
| - **DDIM 30 steps** + CFG: fast generation |
|
|
| ## Usage |
| ```python |
| python infer.py --ckpt model.pt --prompt "1girl, halo, cowboy shot, long hair" --out results -n 4 --cfg 4.0 |
| ``` |
| Use comma-separated Danbooru-style tags: `1girl, halo, cowboy shot, long hair`, `2girls, school uniform`, etc. |
|
|
| ## Files |
| - `model.pt` - full trained model (15 MB) |
| - `infer.py` - inference script |
|
|
