Merge pull request #8 from ModelsLab/qwen-t2i

Feat: EP Qwen Text to Image

Author: Tanmaypatil123

README.md

@@ -24,12 +24,12 @@ Official Python SDK for ModelsLab API - Generate AI content including images, vi
 pip install modelslab_py
 ```
 
-## Quick Start
+## Create a client.
 
 ```python
 from modelslab_py.core.client import Client
 
-client = Client(api_key="your-api-key")
+client = Client(api_key="your_api_key")
 ```
 
 ## Features
@@ -51,7 +51,7 @@ from modelslab_py.core.client import Client
 from modelslab_py.core.apis.image_editing import Image_editing
 from modelslab_py.schemas.image_editing import BackgroundRemoverSchema
 
-client = Client(api_key="your-api-key")
+client = Client(api_key="your_api_key")
 api = Image_editing(client=client, enterprise=False)
 
 schema = BackgroundRemoverSchema(
@@ -69,7 +69,7 @@ print(response)
 from modelslab_py.core.apis.video import Video
 from modelslab_py.schemas.video import Text2Video
 
-client = Client(api_key="your-api-key")
+client = Client(api_key="your_api_key")
 api = Video(client=client, enterprise=False)
 
 schema = Text2Video(
@@ -88,7 +88,7 @@ print(response)
 from modelslab_py.core.apis.interior import Interior
 from modelslab_py.schemas.interior import InteriorSchema
 
-client = Client(api_key="your-api-key")
+client = Client(api_key="your_api_key")
 api = Interior(client=client, enterprise=False)
 
 schema = InteriorSchema(
@@ -106,7 +106,7 @@ print(response)
 from modelslab_py.core.apis.audio import Audio
 from modelslab_py.schemas.audio import Text2Speech
 
-client = Client(api_key="your-api-key")
+client = Client(api_key="your_api_key")
 api = Audio(client=client, enterprise=False)
 
 schema = Text2Speech(
@@ -125,7 +125,7 @@ print(response)
 from modelslab_py.core.apis.three_d import Three_D
 from modelslab_py.schemas.threed import Text23D
 
-client = Client(api_key="your-api-key")
+client = Client(api_key="your_api_key")
 api = Three_D(client=client, enterprise=False)
 
 schema = Text23D(
@@ -144,7 +144,7 @@ print(response)
 from modelslab_py.core.apis.community import Community
 from modelslab_py.schemas.community import Text2Image
 
-client = Client(api_key="your-api-key")
+client = Client(api_key="your_api_key")
 api = Community(client=client, enterprise=False)
 
 schema = Text2Image(

modelslab_py/core/apis/audio.py

@@ -20,54 +20,54 @@ def __init__(self, client: Client = None, enterprise = False ,**kwargs):
 
     def text_to_audio(self, schema: Text2Audio):
         base_endpoint = self.base_url + "text_to_audio"
-        data = schema.dict()
+        data = schema.dict(exclude_none=True)
         response = self.client.post(base_endpoint, data=data)
         return response
 
     def text_to_speech(self, schema: Text2Speech):
         base_endpoint = self.base_url + "text_to_speech"
-        data = schema.dict()
+        data = schema.dict(exclude_none=True)
         response = self.client.post(base_endpoint, data=data)
         return response
 
     def voice2voice(self, schema: Voice2Voice):
         base_endpoint = self.base_url + "voice_to_voice"
-        data = schema.dict()
+        data = schema.dict(exclude_none=True)
         response = self.client.post(base_endpoint, data=data)
         return response
 
     def voice_cover(self, schema: VoiceCover):
         base_endpoint = self.base_url + "voice_cover"
-        data = schema.dict()
+        data = schema.dict(exclude_none=True)
         response = self.client.post(base_endpoint, data=data)
         return response
 
     def music_gen(self, schema: MusicGenSchema):
         base_endpoint = self.base_url + "music_gen"
-        data = schema.dict()
+        data = schema.dict(exclude_none=True)
         response = self.client.post(base_endpoint, data=data)
         return response
 
     def lyrics_gen(self, schema: LyricsGenerator):
         base_endpoint = self.base_url + "lyrics_generator"
-        data = schema.dict()
+        data = schema.dict(exclude_none=True)
         response = self.client.post(base_endpoint, data=data)
         return response
 
     def song_generator(self, schema: SongGenerator):
         base_endpoint = self.base_url + "song_generator"
-        data = schema.dict()
+        data = schema.dict(exclude_none=True)
         response = self.client.post(base_endpoint, data=data)
         return response
 
     def speech_to_text(self, schema: Speech2Text):
         base_endpoint = self.base_url + "speech_to_text"
-        data = schema.dict()
+        data = schema.dict(exclude_none=True)
         response = self.client.post(base_endpoint, data=data)
         return response
 
     def sfx_gen(self, schema: SFX):
         base_endpoint = self.base_url + "sfx"
-        data = schema.dict()
+        data = schema.dict(exclude_none=True)
         response = self.client.post(base_endpoint, data=data)
         return response

modelslab_py/core/apis/community.py

@@ -40,4 +40,12 @@ def controlnet(self, schema: ControlNet):
         base_endpoint = self.base_url + "controlnet"
         data = schema.dict(exclude_none=True)
         response = self.client.post(base_endpoint, data=data)
+        return response
+
+    def qwen_text_to_image(self, schema: QwenText2Image):
+        if not self.enterprise:
+            raise ValueError("Qwen API is only available for enterprise users.")
+        base_endpoint = self.client.base_url + "v1/enterprise/qwen/text2img"
+        data = schema.dict(exclude_none=True)
+        response = self.client.post(base_endpoint, data=data)
         return response

modelslab_py/schemas/audio.py

@@ -258,10 +258,15 @@ class MusicGenSchema(BaseSchema):
 
 
 class LyricsGenerator(BaseSchema):
-    prompt: str = Field(\
+    prompt: str = Field(
         ...,
         description="Text prompt for lyrics generation."
     )
+    length: Optional[str] = Field(
+        None,
+        description="Length of the generated lyrics."
+    )
+
 
 
 class SongGenerator(BaseSchema):
@@ -277,6 +282,10 @@ class SongGenerator(BaseSchema):
         ...,
         description="Text prompt for song generation."
     )
+    model_id: Optional[str] = Field(
+        None,
+        description="Model ID for the song generation."
+    )
     lyrics : Optional[str] = Field(
         None,
         description="Lyrics for the song generation."

modelslab_py/schemas/community.py

@@ -354,4 +354,29 @@ class ControlNet(BaseSchema):
     strength: Optional[float] = Field(
         None,
         description="Strength of the ControlNet model."
+    )
+
+class QwenText2Image(BaseSchema):
+    """
+    Schema for Qwen text-to-image generation.
+    """
+    prompt: str = Field(
+        ...,
+        description="Text prompt for image generation."
+    )
+    negative_prompt: Optional[str] = Field(
+        None,
+        description="Negative prompt for image generation."
+    )
+    width: Optional[int] = Field(
+        512,
+        description="Width of the generated image (max 1024)."
+    )
+    height: Optional[int] = Field(
+        512,
+        description="Height of the generated image (max 1024)."
+    )
+    samples: Optional[int] = Field(
+        1,
+        description="Number of images to generate (1-2)."
     )

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "modelslab_py"
-version = "0.1.4"
+version = "0.1.5"
 description = ""
 authors = ["Tanmay patil <tanmaypatil3151@gmail.com>", "Anurag Kanade <anuragkanade54@gmail.com>"]
 readme = "README.md"