Correct limitations; tag training datasets
Browse files
README.md
CHANGED
|
@@ -95,16 +95,6 @@ The release defaults are 896 × 896, 20 Euler steps, and CFG 4.5. Width and heig
|
|
| 95 |
- [Post-training](https://github.com/Mtrya/inko/blob/main/notes/posttraining.md): the DiffusionART selection campaign, the 24.6k-row rollout pool ([kaupane/inko-rollout-25k](https://huggingface.co/datasets/kaupane/inko-rollout-25k)), the rubric reward, and the two production runs.
|
| 96 |
- [Evaluation](https://github.com/Mtrya/inko/blob/main/notes/evaluation.md): five benchmark catalogs, nine models, and a fixed fine-art comparison suite with per-case analysis.
|
| 97 |
|
| 98 |
-
## Training data
|
| 99 |
-
|
| 100 |
-
The pretraining corpus combines museum collections, recaptioned public datasets and synthetic additions across four domains. The sources available on the Hub:
|
| 101 |
-
|
| 102 |
-
- Chinese painting: [kaupane/chinese-painting-collection](https://huggingface.co/datasets/kaupane/chinese-painting-collection)
|
| 103 |
-
- Western art: [kaupane/wikiart-captions](https://huggingface.co/datasets/kaupane/wikiart-captions)
|
| 104 |
-
- People and anatomy: [kaupane/human-recaption](https://huggingface.co/datasets/kaupane/human-recaption) (a recaption of [OpenFace-CQUPT/HumanCaption-HQ-311K](https://huggingface.co/datasets/OpenFace-CQUPT/HumanCaption-HQ-311K)), [opendiffusionai/cc12m-a_woman](https://huggingface.co/datasets/opendiffusionai/cc12m-a_woman), [kaupane/pexels-people-captions](https://huggingface.co/datasets/kaupane/pexels-people-captions)
|
| 105 |
-
- World knowledge: [kaupane/relaion-art-recap-zh](https://huggingface.co/datasets/kaupane/relaion-art-recap-zh), [Spawning/PD12M](https://huggingface.co/datasets/Spawning/PD12M), [sirus/inaturalist-2024-2.8k-claude-opus-5-recaptioned](https://huggingface.co/datasets/sirus/inaturalist-2024-2.8k-claude-opus-5-recaptioned), [sirus/megalith-10m-5.5k-claude-opus-5-recaptioned](https://huggingface.co/datasets/sirus/megalith-10m-5.5k-claude-opus-5-recaptioned), [kaupane/vintage-photography-captions](https://huggingface.co/datasets/kaupane/vintage-photography-captions), [kaupane/z-image-turbo-gen](https://huggingface.co/datasets/kaupane/z-image-turbo-gen)
|
| 106 |
-
- Post-training rollout pool: [kaupane/inko-rollout-25k](https://huggingface.co/datasets/kaupane/inko-rollout-25k)
|
| 107 |
-
|
| 108 |
## Limitations
|
| 109 |
|
| 110 |
- Exact rendered text and spatial relations remain weak.
|
|
|
|
| 95 |
- [Post-training](https://github.com/Mtrya/inko/blob/main/notes/posttraining.md): the DiffusionART selection campaign, the 24.6k-row rollout pool ([kaupane/inko-rollout-25k](https://huggingface.co/datasets/kaupane/inko-rollout-25k)), the rubric reward, and the two production runs.
|
| 96 |
- [Evaluation](https://github.com/Mtrya/inko/blob/main/notes/evaluation.md): five benchmark catalogs, nine models, and a fixed fine-art comparison suite with per-case analysis.
|
| 97 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 98 |
## Limitations
|
| 99 |
|
| 100 |
- Exact rendered text and spatial relations remain weak.
|