Upload folder using huggingface_hub

README.md

@@ -1,19 +1,19 @@
 ---
 license: apache-2.0
 ---
-# Templates - Meme Panda (FLUX.2-klein-base-4B)
+# Templates-魔性熊猫（FLUX.2-klein-base-4B）
 
-This model is part of the first batch of open-source Diffusion Templates models from [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio). It's an Easter egg model capable of generating various meme-style panda head images.
+本模型是 [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio) 开源的首批 Diffusion Templates 系列模型。这是一个彩蛋模型，能够生成各种魔性的熊猫头表情包。
 
-## Demo Results
+## 效果展示
 
 |Prompt: A meme with a happy expression.|Prompt: A meme with a sleepy expression.|Prompt: A meme with a surprised expression.|
 |-|-|-|
 |![](./assets/image_PandaMeme_happy.jpg)|![](./assets/image_PandaMeme_sleepy.jpg)|![](./assets/image_PandaMeme_surprised.jpg)|
 
-## Inference Code
+## 推理代码
 
-* Install [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio)
+* 安装 [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio)
 
 ```
 git clone https://github.com/modelscope/DiffSynth-Studio.git
@@ -21,13 +21,12 @@ cd DiffSynth-Studio
 pip install -e .
 ```
 
-* Direct inference (requires 40GB GPU memory)
+* 直接推理，需 40G 显存
 
 ```python
 from diffsynth.diffusion.template import TemplatePipeline
 from diffsynth.pipelines.flux2_image import Flux2ImagePipeline, ModelConfig
 import torch
-```
 
 pipe = Flux2ImagePipeline.from_pretrained(
     torch_dtype=torch.bfloat16,
@@ -70,7 +69,7 @@ image = template(
 image.save("image_PandaMeme_surprised.jpg")
 ```
 
-* Enable lazy loading and memory management, requires 24G GPU memory
+* 开启惰性加载和显存管理，需 24G 显存
 
 ```python
 from diffsynth.diffusion.template import TemplatePipeline