feat: Interior: obj remover, interior_mixer, video/watermark-remover,…

README.md

@@ -13,3 +13,171 @@
     <img src="https://img.shields.io/badge/GitHub-ModelsLab-181717?style=for-the-badge&logo=github&logoColor=white" alt="GitHub">
   </a>
 </div>
+
+# ModelsLab Python SDK
+
+Official Python SDK for ModelsLab API - Generate AI content including images, videos, audio, 3D models, and more.
+
+## Installation
+
+```bash
+pip install modelslab_py
+```
+
+## Quick Start
+
+```python
+from modelslab_py.core.client import Client
+
+client = Client(api_key="your-api-key")
+```
+
+## Features
+
+- Image Generation and Editing
+- Video Generation
+- Audio Processing
+- 3D Model Generation
+- Interior Design
+- Deepfake Operations
+- Community Models Integration
+
+## Usage Examples
+
+### Image Editing
+
+```python
+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")
+api = Image_editing(client=client, enterprise=False)
+
+schema = BackgroundRemoverSchema(
+    image="https://example.com/image.jpg",
+    base64=False
+)
+
+response = api.background_remover(schema=schema)
+print(response)
+```
+
+### Video Generation
+
+```python
+from modelslab_py.core.apis.video import Video
+from modelslab_py.schemas.video import Text2Video
+
+client = Client(api_key="your-api-key")
+api = Video(client=client, enterprise=False)
+
+schema = Text2Video(
+    model_id="zeroscope",
+    prompt="a cat walking in a garden",
+    num_frames=30
+)
+
+response = api.text_to_video(schema=schema)
+print(response)
+```
+
+### Interior Design
+
+```python
+from modelslab_py.core.apis.interior import Interior
+from modelslab_py.schemas.interior import InteriorSchema
+
+client = Client(api_key="your-api-key")
+api = Interior(client=client, enterprise=False)
+
+schema = InteriorSchema(
+    prompt="modern minimalist bedroom",
+    init_image="https://example.com/room.jpg"
+)
+
+response = api.interior(schema=schema)
+print(response)
+```
+
+### Audio Processing
+
+```python
+from modelslab_py.core.apis.audio import Audio
+from modelslab_py.schemas.audio import Text2Speech
+
+client = Client(api_key="your-api-key")
+api = Audio(client=client, enterprise=False)
+
+schema = Text2Speech(
+    prompt="Hello, welcome to ModelsLab",
+    voice_id="madison",
+    language="english"
+)
+
+response = api.text_to_speech(schema=schema)
+print(response)
+```
+
+### 3D Generation
+
+```python
+from modelslab_py.core.apis.three_d import Three_D
+from modelslab_py.schemas.threed import Text23D
+
+client = Client(api_key="your-api-key")
+api = Three_D(client=client, enterprise=False)
+
+schema = Text23D(
+    prompt="a wooden chair",
+    model_id="meshy-4",
+    output_format="obj"
+)
+
+response = api.text_to_3d(schema=schema)
+print(response)
+```
+
+### Community Models
+
+```python
+from modelslab_py.core.apis.community import Community
+from modelslab_py.schemas.community import Text2Image
+
+client = Client(api_key="your-api-key")
+api = Community(client=client, enterprise=False)
+
+schema = Text2Image(
+    prompt="a beautiful landscape",
+    model_id="midjourney",
+    width=512,
+    height=512
+)
+
+response = api.text_to_image(schema=schema)
+print(response)
+```
+
+## API Categories
+
+- **Image Editing**: Background removal, super resolution, inpainting, outpainting
+- **Video**: Text-to-video, image-to-video, watermark removal
+- **Audio**: Text-to-speech, voice conversion, music generation
+- **Interior**: Room design, floor planning, object placement
+- **3D**: Text-to-3D, image-to-3D model generation
+- **Deepfake**: Face swapping, video manipulation
+- **Community**: Access to community-trained models
+
+## Documentation
+
+For detailed documentation, visit [docs.modelslab.com](https://docs.modelslab.com/sdk/python)
+
+## Support
+
+- Discord: [Join our community](https://discord.gg/ujtGyjY2)
+- Twitter: [@ModelsLabAI](https://x.com/ModelsLabAI)
+- GitHub: [ModelsLab](https://github.com/ModelsLab)
+
+## License
+
+See LICENSE file for details.

modelslab_py/core/apis/image_editing.py

@@ -70,4 +70,16 @@ def flux_headshot(self, schema: FluxHeadshotSchema):
         base_endpoint = self.base_url + "flux_headshot"
         data = schema.dict()
         response = self.client.post(base_endpoint, data=data)
+        return response
+
+    def qwen_edit(self, schema: QwenEditSchema):
+        base_endpoint = self.base_url + "qwen_edit"
+        data = schema.dict()
+        response = self.client.post(base_endpoint, data=data)
+        return response
+
+    def caption(self, schema: CaptionSchema):
+        base_endpoint = self.base_url + "caption"
+        data = schema.dict()
+        response = self.client.post(base_endpoint, data=data)
         return response

modelslab_py/core/apis/interior.py

@@ -3,7 +3,9 @@
     ScenarioSchema,
     FloorSchema,
     RoomDecoratorSchema,
-    InteriorSchema
+    InteriorSchema,
+    ObjectRemovalSchema,
+    InteriorMixerSchema
 
 )
 from modelslab_py.core.client import Client
@@ -60,4 +62,15 @@ def room_decorator(self,schema : RoomDecoratorSchema):
         data = schema.dict()
         response = self.client.post(base_endpoint, data=data)
         return response
-
+
+    def object_removal(self, schema: ObjectRemovalSchema):
+        base_endpoint = self.base_url + "object_removal"
+        data = schema.dict()
+        response = self.client.post(base_endpoint, data=data)
+        return response
+
+    def interior_mixer(self, schema: InteriorMixerSchema):
+        base_endpoint = self.base_url + "interior_mixer"
+        data = schema.dict()
+        response = self.client.post(base_endpoint, data=data)
+        return response

modelslab_py/core/apis/video.py

@@ -2,7 +2,7 @@
 
 from modelslab_py.core.client import Client
 import time
-from modelslab_py.schemas.video import Text2Video, Image2Video
+from modelslab_py.schemas.video import Text2Video, Image2Video, WatermarkRemoverSchema
 from modelslab_py.core.apis.base import BaseAPI
 
 
@@ -30,4 +30,10 @@ def image_to_video(self, schema: Image2Video):
         base_endpoint = self.base_url + "img2video"
         data = schema.dict()
         response = self.client.post(base_endpoint, data=data)
+        return response
+
+    def watermark_remover(self, schema: WatermarkRemoverSchema):
+        base_endpoint = self.base_url + "watermark_remover"
+        data = schema.dict()
+        response = self.client.post(base_endpoint, data=data)
         return response

modelslab_py/schemas/image_editing.py

@@ -455,7 +455,7 @@ class FluxHeadshotSchema(BaseSchema):
         description="Number of samples for the face generation."
     )
     safety_checker: Optional[bool] = Field(
-        True,   
+        True,
         description="Whether to use safety checker."
     )
     safety_checker_type: Optional[str] = Field(
@@ -469,4 +469,38 @@ class FluxHeadshotSchema(BaseSchema):
     style: Optional[str] = Field(
         "realistic",
         description="Style of the face generation."
+    )
+
+class QwenEditSchema(BaseSchema):
+    """
+    Schema for Qwen Edit.
+    """
+    prompt: str = Field(
+        ...,
+        description="The text prompt describing the content you want in the generated image."
+    )
+    init_image: List[str] = Field(
+        ...,
+        description="Link the image you want your generations to edit and manipulate."
+    )
+    base64: Optional[bool] = Field(
+        False,
+        description="Whether to return the image as base64."
+    )
+
+class CaptionSchema(BaseSchema):
+    """
+    Schema for image caption generation.
+    """
+    init_image: str = Field(
+        ...,
+        description="Link the image you want your generate prompt from. Available formats: `png`, `jpeg`, `jpg`"
+    )
+    length: Optional[str] = Field(
+        "normal",
+        description="The length of the caption."
+    )
+    base64: Optional[bool] = Field(
+        False,
+        description="Whether to return the image as base64."
     )

modelslab_py/schemas/interior.py

@@ -214,4 +214,58 @@ class ScenarioSchema(BaseSchema):
     scenario : str = Field(
         None,
         description="Scenario for the generation."
+    )
+
+class ObjectRemovalSchema(BaseSchema):
+    """
+    Schema for object removal from images.
+    """
+    init_image: str = Field(
+        ...,
+        description="Image from which object will be removed."
+    )
+    object_name: str = Field(
+        ...,
+        description="Object name on the image that needs to be removed."
+    )
+    base64: Optional[bool] = Field(
+        False,
+        description="Whether to return the image as base64."
+    )
+
+class InteriorMixerSchema(BaseSchema):
+    """
+    Schema for interior mixer.
+    """
+    init_image: str = Field(
+        ...,
+        description="Room image in which object wants to be added."
+    )
+    object_image: str = Field(
+        ...,
+        description="Object which we want to add."
+    )
+    prompt: str = Field(
+        ...,
+        description="Prompt required for generation."
+    )
+    width: Optional[int] = Field(
+        None,
+        description="Width of output image. Min: 512, Max: 2048. If not provided, uses original image resolution."
+    )
+    height: Optional[int] = Field(
+        None,
+        description="Height of the output image. Min: 512, Max: 2048. If not provided, uses original image resolution."
+    )
+    guidance_scale: Optional[int] = Field(
+        None,
+        description="The scale for classifier-free guidance."
+    )
+    num_inference_steps: Optional[int] = Field(
+        8,
+        description="Number of inference steps required for generation."
+    )
+    base64: Optional[bool] = Field(
+        False,
+        description="Whether to return the image as base64."
     )

modelslab_py/schemas/video.py

@@ -157,3 +157,12 @@ class Text2VideoUltra(BaseSchema):
         None,
         description="Whether to apply sample shift."
     )
+
+class WatermarkRemoverSchema(BaseSchema):
+    """
+    Schema for watermark removal from videos.
+    """
+    init_video: str = Field(
+        ...,
+        description="URL of the initial video with watermark."
+    )

pyproject.toml

@@ -1,8 +1,8 @@
 [tool.poetry]
 name = "modelslab_py"
-version = "0.1.1"
+version = "0.1.2"
 description = ""
-authors = ["Tanmay patil <tanmaypatil3151@gmail.com>"]
+authors = ["Tanmay patil <tanmaypatil3151@gmail.com>", "Anurag Kanade <anuragkanade54@gmail.com>"]
 readme = "README.md"
 
 [tool.poetry.dependencies]