add model

README.md

@@ -1,3 +1,59 @@
 ---
 license: apache-2.0
+tags:
+- pytorch
+- diffusers
+- text-to-image
 ---
+
+# Chinese ControlNet Model (Canny)
+
+## 简介 Brief Introduction
+
+我们开源了一个中文 ControlNet 模型，该模型适配 diffusion 模型 `alibaba-pai/pai-diffusion-artist-large-zh`，您可以使用该模型控制 diffusion 模型生成的图像。
+
+We release a Chinese ControlNet model, which works with diffusion model `alibaba-pai/pai-diffusion-artist-large-zh`. You can use this model to control the diffusion model generating images as you wish.
+
+* Github: [EasyNLP](https://github.com/alibaba/EasyNLP)
+
+## 使用 Usage
+
+```python
+from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
+from transformers import pipeline
+from PIL import Image
+import numpy as np
+import cv2
+
+
+def to_canny(image):
+    low_threshold = 100
+    high_threshold = 200
+    image = np.array(image)
+    image = cv2.Canny(image, low_threshold, high_threshold)
+    image = image[:, :, None]
+    image = np.concatenate([image, image, image], axis=2)
+    image = Image.fromarray(image)
+    return image
+
+
+controlnet_id = "alibaba-pai/pai-diffusion-artist-large-zh-controlnet-canny"
+controlnet = ControlNetModel.from_pretrained(controlnet_id)
+model_id = "alibaba-pai/pai-diffusion-artist-large-zh"
+pipe = StableDiffusionControlNetPipeline.from_pretrained(model_id, controlnet=controlnet)
+pipe = pipe.to("cuda")
+
+image = Image.open("image.png")
+controlnet_image = to_canny(image)
+prompt = "白色羽毛的小鸟"
+image = pipe(prompt, controlnet_image).images[0]
+
+controlnet_image.save("image_canny.png")
+image.save("image_canny_output.png")
+```
+
+## 使用须知 Notice for Use
+
+使用上述模型需遵守[AIGC模型开源特别条款](https://terms.alicdn.com/legal-agreement/terms/common_platform_service/20230505180457947/20230505180457947.html)。
+
+If you want to use this model, please read this [document](https://terms.alicdn.com/legal-agreement/terms/common_platform_service/20230505180457947/20230505180457947.html) carefully and abide by the terms.

config.json

@@ -0,0 +1,42 @@
+{
+  "_class_name": "ControlNetModel",
+  "_diffusers_version": "0.16.1",
+  "act_fn": "silu",
+  "attention_head_dim": 8,
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "class_embed_type": null,
+  "conditioning_embedding_out_channels": [
+    16,
+    32,
+    96,
+    256
+  ],
+  "controlnet_conditioning_channel_order": "rgb",
+  "cross_attention_dim": 768,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "global_pool_conditions": false,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_scale_factor": 1,
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_time_scale_shift": "default",
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1237f33b79961e64da25b69352718568aba575ba9a80a0b38befb06d773632a9
+size 1445253593