Update README.md
Browse files
README.md
CHANGED
|
@@ -2,12 +2,12 @@
|
|
| 2 |
|
| 3 |
| 文件名 (Filename) | 中文介绍 (Chinese Description) | English Description |
|
| 4 |
| :------------------------------------------------------------------------------------------ | :-------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------ |
|
| 5 |
-
| [`
|
| 6 |
-
| [`
|
| 7 |
|
| 8 |
-
### 模型介绍:neta-art/
|
| 9 |
|
| 10 |
-
欢迎体验 **neta-art/
|
| 11 |
|
| 12 |
这是一款由 [Nieta.art](https://nieta.art/) 团队基于优秀的开源模型 [Lumina-Image-2.0 by Alpha-VLLM](https://github.com/Alpha-VLLM/Lumina-Image-2.0) 进一步训练的二次元文本生成图像(T2I)模型。在训练过程中,我们利用了大量丰富、多样化的二次元图像数据集,并为其配备了高质量的自然语言处理(NLP)标签,力求模型能够更好地理解和诠释二次元相关的文本描述。
|
| 13 |
|
|
@@ -35,9 +35,9 @@
|
|
| 35 |
|
| 36 |
-----
|
| 37 |
|
| 38 |
-
### Model Introduction: neta-art/
|
| 39 |
|
| 40 |
-
Welcome to **neta-art/
|
| 41 |
|
| 42 |
This is an anime-style text-to-image (T2I) model further trained by the [Nieta.art](https://nieta.art/) team, based on the excellent open-source model [Lumina-Image-2.0 by Alpha-VLLM](https://github.com/Alpha-VLLM/Lumina-Image-2.0). During the training process, we utilized an extensive, rich, and diverse dataset of anime images, paired with high-quality Natural Language Processing (NLP) tags, striving for the model to better understand and interpret anime-related text descriptions.
|
| 43 |
|
|
|
|
| 2 |
|
| 3 |
| 文件名 (Filename) | 中文介绍 (Chinese Description) | English Description |
|
| 4 |
| :------------------------------------------------------------------------------------------ | :-------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------ |
|
| 5 |
+
| [`NetaAniLumina_Alpha_full_round7_ep4_s68303.pth`](./NetaAniLumina_Alpha_full_round7_ep4_s68303.pth) | 截止至5月22日最新一个完整的epoch,分辨率为1280\*1280。 | The latest complete epoch as of May 22nd, with a resolution of 1280\*1280. |
|
| 6 |
+
| [`NetaAniLumina_Alpha_full_round5_ep5_s182000.pth`](./NetaAniLumina_Alpha_full_round5_ep5_s182000.pth) | 截止至5月8日,此为分辨率提升前的最后一个检查点(ckpt),分辨率为1024\*1024。 | As of May 8th, this was the last checkpoint (ckpt) before the resolution increase, with a resolution of 1024\*1024. |
|
| 7 |
|
| 8 |
+
### 模型介绍:neta-art/NetaAniLumina_Alpha
|
| 9 |
|
| 10 |
+
欢迎体验 **neta-art/NetaAniLumina_Alpha**!
|
| 11 |
|
| 12 |
这是一款由 [Nieta.art](https://nieta.art/) 团队基于优秀的开源模型 [Lumina-Image-2.0 by Alpha-VLLM](https://github.com/Alpha-VLLM/Lumina-Image-2.0) 进一步训练的二次元文本生成图像(T2I)模型。在训练过程中,我们利用了大量丰富、多样化的二次元图像数据集,并为其配备了高质量的自然语言处理(NLP)标签,力求模型能够更好地理解和诠释二次元相关的文本描述。
|
| 13 |
|
|
|
|
| 35 |
|
| 36 |
-----
|
| 37 |
|
| 38 |
+
### Model Introduction: neta-art/NetaAniLumina\_Alpha
|
| 39 |
|
| 40 |
+
Welcome to **neta-art/NetaAniLumina\_Alpha**\!
|
| 41 |
|
| 42 |
This is an anime-style text-to-image (T2I) model further trained by the [Nieta.art](https://nieta.art/) team, based on the excellent open-source model [Lumina-Image-2.0 by Alpha-VLLM](https://github.com/Alpha-VLLM/Lumina-Image-2.0). During the training process, we utilized an extensive, rich, and diverse dataset of anime images, paired with high-quality Natural Language Processing (NLP) tags, striving for the model to better understand and interpret anime-related text descriptions.
|
| 43 |
|