Downloads · 30 days
257
55% of all-time downloads
pikadiffusion
simonko912/pikadiffusion
pikadiffusion is a text-to-image model from simonko912. Use it when you need an image from a text prompt. The card lists the license as apache-2.0.
All-time downloads
466
Public
Parameters
129M
3.6 GB on disk
Likes
3
Public
Repo makeup
Click a slice to open those files.
.pt2.1 GB · 80%
At a glance
- Task
- Text-to-Image
- License
- apache-2.0
- Access
- Public
- Created
- Jul 20, 2026
- Updated
- Jul 27, 2026
- SHA
- b5141a3f
Try a prompt
Spaces
Model card
From the Hugging Face model README
Pikadiffusion
Model details
- Parameters: ~129M
- Resolution: 128x128
- Dataset: 6576 Pokémon images + captions
- Epochs: 100
- Text encoder: OpenAI CLIP ViT-B/32
- Diffusion: DDPM
- EMA: Yes
- Loss after training: 0.017578418961433816
Datasets
- hf.co/TeeA/Pokemon-Captioning-Classification
- hf.co/GabeHD/pokemon-type-captions
- github.com/rileynwong/pokemon-images-dataset-by-type
Notes
lowram.py is reccomended for devices under 4GB of ram. Uses around 2gb peak and 1gb while generating.<br>
Check out the space! Takes 5s per image https://huggingface.co/spaces/simonko912/pikadiffusion
<Gallery />
- Task
- Text-to-Image
- License
- apache-2.0
- Languages
- en
- Created
- Jul 20, 2026
- Updated
- Jul 27, 2026