model card: drop demo link until the Space exists
Browse files
README.md
CHANGED
|
@@ -23,7 +23,6 @@ A 210M-parameter text-to-image diffusion transformer trained from scratch on one
|
|
| 23 |
flan-t5-base text encoder; the transformer, recipe, data pipeline and evaluation are original.
|
| 24 |
|
| 25 |
- Code, figures and every design decision with sources: https://github.com/ivanmikhnenkov/tinydit (tag `v1-pretrain`)
|
| 26 |
-
- Try it: https://huggingface.co/spaces/ivanmikhnenkov/tinydit
|
| 27 |
- Author: https://ivanmikhnenkov.com
|
| 28 |
|
| 29 |
## Results (held-out prompts, 20 Euler steps, CFG 4, shift 2.8)
|
|
|
|
| 23 |
flan-t5-base text encoder; the transformer, recipe, data pipeline and evaluation are original.
|
| 24 |
|
| 25 |
- Code, figures and every design decision with sources: https://github.com/ivanmikhnenkov/tinydit (tag `v1-pretrain`)
|
|
|
|
| 26 |
- Author: https://ivanmikhnenkov.com
|
| 27 |
|
| 28 |
## Results (held-out prompts, 20 Euler steps, CFG 4, shift 2.8)
|