Downloads · 30 days
7
10% of all-time downloads
animegen-latent-diffusion
Asilarkness/animegen-latent-diffusion
animegen-latent-diffusion is a text-to-image model from Asilarkness. Use it when you need an image from a text prompt. The card lists the license as mit.
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).
All-time downloads
67
Public
Repo size
30.7 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt16.2 MB · 97%
At a glance
- Task
- Text-to-Image
- License
- mit
- Model type
- latent-diffusion
- Access
- Public
- Created
- Aug 15, 2026
- Updated
- Aug 15, 2026
- SHA
- 99de5f63
Model card
From the Hugging Face model README
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
- Autoencoder - 96x96 -> 64-channel latent. Reconstruction PSNR 27.8 dB.
- GRU tag encoder - comma-separated Danbooru tags -> conditioning vector.
- 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 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
- Task
- Text-to-Image
- Type
- latent-diffusion
- License
- mit
- Languages
- en
- Created
- Aug 15, 2026
- Updated
- Aug 15, 2026