Restructure documentation, validate metadata removal, consolidate assets

This commit is contained in:
Victor Kuznetsov
2026-07-25 21:08:04 -07:00
parent 214c9bb3e7
commit 03cd00f132
172 changed files with 2356 additions and 2863 deletions
+37
View File
@@ -0,0 +1,37 @@
# Pipeline fidelity evaluation
This evaluation compares diffusion pipelines with
`scripts/fidelity_metrics.py`. The images themselves have one canonical home
in `data/synthid/originals/`; this directory stores only evaluation-specific
ground truth and instructions.
| Original | Provider | Content | Exercises |
| --- | --- | --- | --- |
| `ChatGPT Image May 31, 2026, 02_03_55 PM.png` | OpenAI | Multilingual typography | Text preservation |
| `Gemini_Generated_Image_633uuy633uuy633u.png` | Google | Landscape with a Chinese sign | CJK text preservation |
| `Gemini_Generated_Image_y48j3cy48j3cy48j.png` | Google | Portrait grid | Face identity and skin texture |
## Text ground truth
`ground-truth.json` contains hand-verified OCR for the two text-bearing
originals. To regenerate an OCR seed:
```bash
uv run scripts/fidelity_metrics.py ocr \
"data/synthid/originals/ChatGPT Image May 31, 2026, 02_03_55 PM.png" \
data/synthid/originals/Gemini_Generated_Image_633uuy633uuy633u.png \
--langs en,ru,ch \
--out data/evaluations/fidelity/ground-truth.json
```
Verify and correct the generated text by hand before using it as ground truth.
## Compare
```bash
uv run scripts/fidelity_metrics.py compare \
--original data/synthid/originals/Gemini_Generated_Image_y48j3cy48j3cy48j.png \
--variant controlnet=<out>.png \
--variant qwen=<out>.png \
--ocr-langs ""
```
@@ -0,0 +1,4 @@
{
"ChatGPT Image May 31, 2026, 02_03_55 PM.png": "This is a longer sample text in English.\nTypography can flow smoothly from large to medium size.\nSmaller lines help demonstrate hierarchy, rhythm, and clarity.\nEven the finest text should remain clean and readable.\n这是一段较长的中文示例文本。\n排版可以从大字号逐渐过渡到中字号。\n更小的文字能够展示层次、节奏与清晰度。\n即使是最小的一行,也应该保持清楚易读。\nЭто более длинный пример текста на русском языке.\nТипографика может плавно переходить от крупного размера к среднему.\nБолее мелкие строки показывают иерархию, ритм и ясность.\nДаже самый маленький текст должен оставаться чистым и читаемым.",
"Gemini_Generated_Image_633uuy633uuy633u.png": "每天都是一个新的机会。\n用微笑开始它。\n世界也会向你微笑。"
}