Update README.md
Browse files
README.md
CHANGED
|
@@ -4,7 +4,9 @@ license: apache-2.0
|
|
| 4 |
|
| 5 |
## NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale
|
| 6 |
|
| 7 |
-
[Homepage](https://stepfun.ai/research/en/nextstep-1)
|
|
|
|
|
|
|
| 8 |
|
| 9 |
We introduce **NextStep-1**, a 14B autoregressive model paired with a 157M flow matching head, training on discrete text tokens and continuous image tokens with next-token prediction objectives.
|
| 10 |
**NextStep-1** achieves state-of-the-art performance for autoregressive models in text-to-image generation tasks, exhibiting strong capabilities in high-fidelity image synthesis.
|
|
@@ -13,7 +15,7 @@ We introduce **NextStep-1**, a 14B autoregressive model paired with a 157M flow
|
|
| 13 |
<img src="assets/teaser.jpg" class="interpolation-image" alt="arch." width="100%" />
|
| 14 |
</div>
|
| 15 |
|
| 16 |
-
##
|
| 17 |
|
| 18 |
To avoid potential errors when loading and running your models, we recommend using the following settings:
|
| 19 |
|
|
|
|
| 4 |
|
| 5 |
## NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale
|
| 6 |
|
| 7 |
+
[Homepage](https://stepfun.ai/research/en/nextstep-1)
|
| 8 |
+
| [GitHub](https://github.com/stepfun-ai/NextStep-1)
|
| 9 |
+
| [Paper](https://arxiv.org/abs/2508.10711)
|
| 10 |
|
| 11 |
We introduce **NextStep-1**, a 14B autoregressive model paired with a 157M flow matching head, training on discrete text tokens and continuous image tokens with next-token prediction objectives.
|
| 12 |
**NextStep-1** achieves state-of-the-art performance for autoregressive models in text-to-image generation tasks, exhibiting strong capabilities in high-fidelity image synthesis.
|
|
|
|
| 15 |
<img src="assets/teaser.jpg" class="interpolation-image" alt="arch." width="100%" />
|
| 16 |
</div>
|
| 17 |
|
| 18 |
+
## Environment Setup
|
| 19 |
|
| 20 |
To avoid potential errors when loading and running your models, we recommend using the following settings:
|
| 21 |
|