feat: add siliconflow text2img tool (#7612)

api/core/tools/provider/builtin/siliconflow/siliconflow.py

@@ -0,0 +1,19 @@
+import requests
+
+from core.tools.errors import ToolProviderCredentialValidationError
+from core.tools.provider.builtin_tool_provider import BuiltinToolProviderController
+
+
+class SiliconflowProvider(BuiltinToolProviderController):
+    def _validate_credentials(self, credentials: dict) -> None:
+        url = "https://api.siliconflow.cn/v1/models"
+        headers = {
+            "accept": "application/json",
+            "authorization": f"Bearer {credentials.get('siliconFlow_api_key')}",
+        }
+
+        response = requests.get(url, headers=headers)
+        if response.status_code != 200:
+            raise ToolProviderCredentialValidationError(
+                "SiliconFlow API key is invalid"
+            )

api/core/tools/provider/builtin/siliconflow/siliconflow.yaml

@@ -0,0 +1,21 @@
+identity:
+  author: hjlarry
+  name: siliconflow
+  label:
+    en_US: SiliconFlow
+    zh_CN: 硅基流动
+  description:
+    en_US: The image generation API provided by SiliconFlow includes Flux and Stable Diffusion models.
+    zh_CN: 硅基流动提供的图片生成 API，包含 Flux 和 Stable Diffusion 模型。
+  icon: icon.svg
+  tags:
+    - image
+credentials_for_provider:
+  siliconFlow_api_key:
+    type: secret-input
+    required: true
+    label:
+      en_US: SiliconFlow API Key
+    placeholder:
+      en_US: Please input your SiliconFlow API key
+    url: https://cloud.siliconflow.cn/account/ak

api/core/tools/provider/builtin/siliconflow/tools/flux.py

@@ -0,0 +1,44 @@
+from typing import Any, Union
+
+import requests
+
+from core.tools.entities.tool_entities import ToolInvokeMessage
+from core.tools.tool.builtin_tool import BuiltinTool
+
+FLUX_URL = (
+    "https://api.siliconflow.cn/v1/black-forest-labs/FLUX.1-schnell/text-to-image"
+)
+
+
+class FluxTool(BuiltinTool):
+
+    def _invoke(
+        self, user_id: str, tool_parameters: dict[str, Any]
+    ) -> Union[ToolInvokeMessage, list[ToolInvokeMessage]]:
+
+        headers = {
+            "accept": "application/json",
+            "content-type": "application/json",
+            "authorization": f"Bearer {self.runtime.credentials['siliconFlow_api_key']}",
+        }
+
+        payload = {
+            "prompt": tool_parameters.get("prompt"),
+            "image_size": tool_parameters.get("image_size", "1024x1024"),
+            "seed": tool_parameters.get("seed"),
+            "num_inference_steps": tool_parameters.get("num_inference_steps", 20),
+        }
+
+        response = requests.post(FLUX_URL, json=payload, headers=headers)
+        if response.status_code != 200:
+            return self.create_text_message(f"Got Error Response:{response.text}")
+
+        res = response.json()
+        result = [self.create_json_message(res)]
+        for image in res.get("images", []):
+            result.append(
+                self.create_image_message(
+                    image=image.get("url"), save_as=self.VARIABLE_KEY.IMAGE.value
+                )
+            )
+        return result

api/core/tools/provider/builtin/siliconflow/tools/flux.yaml

@@ -0,0 +1,73 @@
+identity:
+  name: flux
+  author: hjlarry
+  label:
+    en_US: Flux
+  icon: icon.svg
+description:
+  human:
+    en_US: Generate image via SiliconFlow's flux schnell.
+  llm: This tool is used to generate image from prompt via SiliconFlow's flux schnell model.
+parameters:
+  - name: prompt
+    type: string
+    required: true
+    label:
+      en_US: prompt
+      zh_Hans: 提示词
+    human_description:
+      en_US: The text prompt used to generate the image.
+      zh_Hans: 用于生成图片的文字提示词
+    llm_description: this prompt text will be used to generate image.
+    form: llm
+  - name: image_size
+    type: select
+    required: true
+    options:
+      - value: 1024x1024
+        label:
+          en_US: 1024x1024
+      - value: 768x1024
+        label:
+          en_US: 768x1024
+      - value: 576x1024
+        label:
+          en_US: 576x1024
+      - value: 512x1024
+        label:
+          en_US: 512x1024
+      - value: 1024x576
+        label:
+          en_US: 1024x576
+      - value: 768x512
+        label:
+          en_US: 768x512
+    default: 1024x1024
+    label:
+      en_US: Choose Image Size
+      zh_Hans: 选择生成的图片大小
+    form: form
+  - name: num_inference_steps
+    type: number
+    required: true
+    default: 20
+    min: 1
+    max: 100
+    label:
+      en_US: Num Inference Steps
+      zh_Hans: 生成图片的步数
+    form: form
+    human_description:
+      en_US: The number of inference steps to perform. More steps produce higher quality but take longer.
+      zh_Hans: 执行的推理步骤数量。更多的步骤可以产生更高质量的结果，但需要更长的时间。
+  - name: seed
+    type: number
+    min: 0
+    max: 9999999999
+    label:
+      en_US: Seed
+      zh_Hans: 种子
+    human_description:
+      en_US: The same seed and prompt can produce similar images.
+      zh_Hans: 相同的种子和提示可以产生相似的图像。
+    form: form

api/core/tools/provider/builtin/siliconflow/tools/stable_diffusion.py

@@ -0,0 +1,51 @@
+from typing import Any, Union
+
+import requests
+
+from core.tools.entities.tool_entities import ToolInvokeMessage
+from core.tools.tool.builtin_tool import BuiltinTool
+
+SDURL = {
+    "sd_3": "https://api.siliconflow.cn/v1/stabilityai/stable-diffusion-3-medium/text-to-image",
+    "sd_xl": "https://api.siliconflow.cn/v1/stabilityai/stable-diffusion-xl-base-1.0/text-to-image",
+}
+
+
+class StableDiffusionTool(BuiltinTool):
+
+    def _invoke(
+        self, user_id: str, tool_parameters: dict[str, Any]
+    ) -> Union[ToolInvokeMessage, list[ToolInvokeMessage]]:
+
+        headers = {
+            "accept": "application/json",
+            "content-type": "application/json",
+            "authorization": f"Bearer {self.runtime.credentials['siliconFlow_api_key']}",
+        }
+
+        model = tool_parameters.get("model", "sd_3")
+        url = SDURL.get(model)
+
+        payload = {
+            "prompt": tool_parameters.get("prompt"),
+            "negative_prompt": tool_parameters.get("negative_prompt", ""),
+            "image_size": tool_parameters.get("image_size", "1024x1024"),
+            "batch_size": tool_parameters.get("batch_size", 1),
+            "seed": tool_parameters.get("seed"),
+            "guidance_scale": tool_parameters.get("guidance_scale", 7.5),
+            "num_inference_steps": tool_parameters.get("num_inference_steps", 20),
+        }
+
+        response = requests.post(url, json=payload, headers=headers)
+        if response.status_code != 200:
+            return self.create_text_message(f"Got Error Response:{response.text}")
+
+        res = response.json()
+        result = [self.create_json_message(res)]
+        for image in res.get("images", []):
+            result.append(
+                self.create_image_message(
+                    image=image.get("url"), save_as=self.VARIABLE_KEY.IMAGE.value
+                )
+            )
+        return result

api/core/tools/provider/builtin/siliconflow/tools/stable_diffusion.yaml

@@ -0,0 +1,121 @@
+identity:
+  name: stable_diffusion
+  author: hjlarry
+  label:
+    en_US: Stable Diffusion
+  icon: icon.svg
+description:
+  human:
+    en_US: Generate image via SiliconFlow's stable diffusion model.
+  llm: This tool is used to generate image from prompt via SiliconFlow's stable diffusion model.
+parameters:
+  - name: prompt
+    type: string
+    required: true
+    label:
+      en_US: prompt
+      zh_Hans: 提示词
+    human_description:
+      en_US: The text prompt used to generate the image.
+      zh_Hans: 用于生成图片的文字提示词
+    llm_description: this prompt text will be used to generate image.
+    form: llm
+  - name: negative_prompt
+    type: string
+    label:
+      en_US: negative prompt
+      zh_Hans: 负面提示词
+    human_description:
+      en_US: Describe what you don't want included in the image.
+      zh_Hans: 描述您不希望包含在图片中的内容。
+    llm_description: Describe what you don't want included in the image.
+    form: llm
+  - name: model
+    type: select
+    required: true
+    options:
+      - value: sd_3
+        label:
+          en_US: Stable Diffusion 3
+      - value: sd_xl
+        label:
+          en_US: Stable Diffusion XL
+    default: sd_3
+    label:
+      en_US: Choose Image Model
+      zh_Hans: 选择生成图片的模型
+    form: form
+  - name: image_size
+    type: select
+    required: true
+    options:
+      - value: 1024x1024
+        label:
+          en_US: 1024x1024
+      - value: 1024x2048
+        label:
+          en_US: 1024x2048
+      - value: 1152x2048
+        label:
+          en_US: 1152x2048
+      - value: 1536x1024
+        label:
+          en_US: 1536x1024
+      - value: 1536x2048
+        label:
+          en_US: 1536x2048
+      - value: 2048x1152
+        label:
+          en_US: 2048x1152
+    default: 1024x1024
+    label:
+      en_US: Choose Image Size
+      zh_Hans: 选择生成图片的大小
+    form: form
+  - name: batch_size
+    type: number
+    required: true
+    default: 1
+    min: 1
+    max: 4
+    label:
+      en_US: Number Images
+      zh_Hans: 生成图片的数量
+    form: form
+  - name: guidance_scale
+    type: number
+    required: true
+    default: 7
+    min: 0
+    max: 100
+    label:
+      en_US: Guidance Scale
+      zh_Hans: 与提示词紧密性
+    human_description:
+      en_US: Classifier Free Guidance. How close you want the model to stick to your prompt when looking for a related image to show you.
+      zh_Hans: 无分类器引导。您希望模型在寻找相关图片向您展示时，与您的提示保持多紧密的关联度。
+    form: form
+  - name: num_inference_steps
+    type: number
+    required: true
+    default: 20
+    min: 1
+    max: 100
+    label:
+      en_US: Num Inference Steps
+      zh_Hans: 生成图片的步数
+    human_description:
+      en_US: The number of inference steps to perform. More steps produce higher quality but take longer.
+      zh_Hans: 执行的推理步骤数量。更多的步骤可以产生更高质量的结果，但需要更长的时间。
+    form: form
+  - name: seed
+    type: number
+    min: 0
+    max: 9999999999
+    label:
+      en_US: Seed
+      zh_Hans: 种子
+    human_description:
+      en_US: The same seed and prompt can produce similar images.
+      zh_Hans: 相同的种子和提示可以产生相似的图像。
+    form: form