Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+as-i-vs-300.png filter=lfs diff=lfs merge=lfs -text
+as-i.png filter=lfs diff=lfs merge=lfs -text

AS-I-300-prior.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14816b89893c8cfeb6e466a10ac46cd64d3f414155238bfd991babbe197089a3
+size 109304673

AS-I-prior.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ed8e3948810cb6b411eb0c89414a222a7f15b2c5af7f6fb411bf913ec92e4a
+size 110273385

AS-I-vae.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3abef8deca23d05c1782666a0db4857b4ddea1d00e5d3c3447574b742e31dd6c
+size 11028119

README.md

@@ -0,0 +1,127 @@
+---
+license: mit
+tags: [text-to-image, diffusion, tiny, from-scratch]
+pipeline_tag: text-to-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.
+
+| | **AS-I** | **AS-I-300** |
+|---|--:|--:|
+| Glyphs it can draw | 1254 | 300 |
+| Training samples per glyph | 36 | **150** |
+| Final val loss | 0.0913 | **0.0374** |
+| Size | 14 MB | 14 MB |
+| Time per image | 186 ms | 192 ms |
+
+![AS-I vs AS-I-300](as-i-vs-300.png)
+
+*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
+
+![AS-I samples](as-i.png)
+
+```python
+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"
+```
+
+| Prompt | What it draws |
+|---|---|
+| `red heart` | a clean, correctly-shaped red heart |
+| `soccer ball` | black-and-white ball, pentagon pattern intact |
+| `rocket` | rocket body with fins and nose cone |
+| `cat face` | orange cat face with ears and whiskers |
+| `a small pizza in the top left on a navy background` | exactly that |
+
+## 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:
+
+| Attribute | AS-I | AS-I-300 |
+|---|--:|--:|
+| background | 100% | 100% |
+| size | 100% | 100% |
+| position | 88% | 93% |
+
+## 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](https://arxiv.org/abs/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
+
+| File | What |
+|---|---|
+| `AS-I-prior.pt` | the 1254-glyph diffusion prior + text encoder |
+| `AS-I-300-prior.pt` | the 300-glyph variant |
+| `AS-I-vae.pt` | the autoencoder (shared by both) |
+
+## Usage
+
+```bash
+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](https://openmoji.org) (CC BY-SA 4.0) — attribute OpenMoji if you
+redistribute renders or derivatives.