---
tags:
  - text-to-image
  - diffusion
  - latent-diffusion
  - pytorch
license: apache-2.0
---

# NanoDiffusion-46M
A ~46M parameter UNet trained from scratch for text-to-image generation
in latent space (SD VAE + CLIP text encoder, both frozen).

**Dataset:** [BitTranslate/Bittensor_subnet_19_06_04_24](https://huggingface.co/datasets/BitTranslate/Bittensor_subnet_19_06_04_24)  
**Trained steps:** 500  
**Image size:** 256px → 32×32 latents

## Architecture

- **UNet base channels:** 128
- **Channel multipliers:** (1, 2, 3, 4)
- **Res blocks per level:** 2
- **Cross-attention (text conditioning):** latent res (8,)
- **VAE (frozen):** `runwayml/stable-diffusion-v1-5` vae subfolder
- **Text encoder (frozen):** CLIP ViT-L/14 from `runwayml/stable-diffusion-v1-5`