artificial-stupidity-image

AS-I — Artificial Stupidity Image

A text-to-image latent diffusion model trained entirely from scratch on a laptop. No Stable Diffusion, no CLIP, no pretrained weights of any kind.

13.7M parameters. 14 MB at int8. 186 ms per image on a CPU.

Two variants are included, and the difference between them is the point.

Top row AS-I, bottom row AS-I-300, same prompts and seed: red heart · pizza · grinning face · cat face · birthday cake · hamburger · strawberry · cookie

Identical architecture, identical compute, identical size — 59% lower loss, and the difference is visible rather than statistical. AS-I-300's strawberry has seeds and a leaf where AS-I's is a red blob; its cookie has chocolate chips; its pizza has pepperoni.

A fixed parameter budget buys a fixed amount of detail. Spreading it over 4× more identities spends it on breadth instead of sharpness. Small models are not bad models — they are models that have to choose.

Example input and output

python sample.py --prompt "red heart"
python sample.py --prompt "a large red heart in the center on a black background"
python sample.py --preset AS-I-300 --prompt "pizza"

The prompt grammar — this is a closed vocabulary

<name>
a <size> <name> in the <position> on a <bg> background

size      small | medium | large
position  top left | top | top right | left | center | right
          bottom left | bottom | bottom right
bg        white | black | navy | grey | cream | teal

Prompt adherence, scored automatically over 120 prompts:

What it cannot do

two astronauts playing chess — nothing. It knows emoji names and placement words. Novel combinations of known words compose fine (pizza in the top left never appeared in training). Novel concepts do not, and no amount of training at this size will change that.

Open-domain text-to-image needs ~1B parameters and ~150,000 A100-hours. This is what the same problem looks like when the budget is a laptop and the rule is that every weight has to be yours.

Architecture

prompt -> word-level text encoder (0.45M params, trained here, NOT CLIP)
       -> cross-attention U-Net (13.2M) on a 16x16x4 latent, 8 DDIM steps
       -> VAE decoder -> 64x64 image

No codebook. The obvious reference (RQ-VAE, arXiv:2203.01941) spends 16,384 codes × 256 dims × 4 quantizers ≈ 16.8M params — about 67 MB — on lookup tables alone, more than this entire model. A continuous 4-channel latent needs no table.

4× downsampling, not 8×. Stable Diffusion uses 8×, but it applies that to 512px images and lands on a 64×64 latent. Applying 8× to a 64px image lands on 8×8 — the same ratio with 64× fewer cells — and reconstructs a rainbow as a brown smear at 21.7 dB. At 4× it is 26.3 dB and colour survives.

Files

Usage

git clone https://github.com/ayushmaninbox/artificial-stupidity
cd artificial-stupidity/as-image-model
pip install -r requirements.txt
python sample.py --prompt "red heart"

License

MIT for code and weights. Training images are rendered from OpenMoji (CC BY-SA 4.0) — attribute OpenMoji if you redistribute renders or derivatives.