--- license: mit pipeline_tag: text-to-image language: - en tags: - image - t2i - text-to-image - custoom-code model-index: - name: PixelModel results: - task: type: text-to-image dataset: name: fid type: fid metrics: - name: fid type: fid value: 566.84 - task: type: text-to-image dataset: name: clip type: clip metrics: - name: clip type: clip value: 0.186 new_version: bench-labs/pixelmodel-v1 ---
| π BenchLabs Leaderboard β’ π Tiny-T2I Leaderboard |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
---
## π Files
```text
model.png β THE MODEL (64Γ3200 px)
model.safetensors β same weights, standard format (generated, see below)
config.json β architecture + parameter-count metadata
main.py β inference, loads model.png
INFERENCE.py β inference, loads model.safetensors
convert_to_safetensors.py β model.png -> model.safetensors
train.py β training
model.py β architecture
dataset/
red.png
red.txt β prompt: "red"
...
```
---
## βοΈ Usage
```bash
python train.py
python train.py --epochs 500 --lr 0.05
python main.py "red"
python main.py "a cat" --out cat.png --scale 8
# equivalent, but loads model.safetensors instead of model.png
python convert_to_safetensors.py
python INFERENCE.py "a cat" --out cat.png --scale 8
```
`main.py` and `INFERENCE.py` produce byte-identical output for the same prompt β they're the same architecture and weights, just loaded from different files.
---
## π Tips
* 6β20 samples are enough
* Simple patterns converge fastest
* 200β500 epochs typical
* Loss < 0.001 is strong for toy datasets
---
*Itβs a toy. Itβs not useful. But it works.*
Bench Labs Β· Simple, Reliable, Open sourced