Downloads · 30 days
13
24% of all-time downloads
NanoDiffusion-46M-1k
FlameF0X/NanoDiffusion-46M-1k
NanoDiffusion-46M-1k is a text-to-image model from FlameF0X. Use it when you need an image from a text prompt. The card lists the license as apache-2.0.
A ~46M parameter UNet trained from scratch for text-to-image generation in latent space (SD VAE + CLIP text encoder, both frozen).
All-time downloads
54
Public
Parameters
45.5M
364 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors182 MB · 100%
At a glance
- Task
- Text-to-Image
- License
- apache-2.0
- Access
- Public
- Created
- Jun 28, 2026
- Updated
- Jun 28, 2026
- SHA
- f78d5750
Model card
From the Hugging Face model README
Mini Latent Diffusion Model
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
Trained steps: 1000
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-v1-5vae subfolder - Text encoder (frozen): CLIP ViT-L/14 from
runwayml/stable-diffusion-v1-5
Inference
from train_mini_ldm import generate
imgs = generate("a sunset over the ocean", "./mini_ldm_output/final")
- Task
- Text-to-Image
- License
- apache-2.0
- Created
- Jun 28, 2026
- Updated
- Jun 28, 2026