datasety 0.1.0__py3-none-any.whl → 0.2.0__py3-none-any.whl

datasety/__init__.py

@@ -1,3 +1,3 @@
 """datasety - CLI tool for dataset preparation: image resizing and captioning."""
 
-__version__ = "0.1.0"
+__version__ = "0.2.0"

datasety/cli.py

@@ -1,10 +1,11 @@
 #!/usr/bin/env python3
 """
-datasety - CLI tool for dataset preparation: image resizing and captioning.
+datasety - CLI tool for dataset preparation: resize, caption, and synthetic generation.
 
 Usage:
     datasety resize --input ./in --output ./out --resolution 768x1024 --crop-position top
     datasety caption --input ./in --output ./out --trigger-word "[trigger]" --florence-2-large
+    datasety synthetic --input ./in --output ./out --prompt "add a winter hat"
 """
 
 import argparse
@@ -283,6 +284,114 @@ def cmd_caption(args):
     print(f"Done! Processed: {processed} images")
 
 
+def cmd_synthetic(args):
+    """Execute the synthetic image generation command."""
+    # Lazy import for faster CLI startup
+    try:
+        import torch
+    except ImportError:
+        print("Error: PyTorch not installed.")
+        print("Run: pip install 'datasety[synthetic]'")
+        sys.exit(1)
+
+    input_dir = Path(args.input)
+    output_dir = Path(args.output)
+
+    if not input_dir.exists():
+        print(f"Error: Input directory '{input_dir}' does not exist.")
+        sys.exit(1)
+
+    output_dir.mkdir(parents=True, exist_ok=True)
+
+    # Determine device
+    if args.device == "cuda" and not torch.cuda.is_available():
+        print("Warning: CUDA not available, falling back to CPU")
+        device = "cpu"
+    else:
+        device = args.device
+
+    # Import the correct pipeline based on model
+    try:
+        from diffusers import QwenImageEditPlusPipeline
+        pipeline_class = QwenImageEditPlusPipeline
+    except ImportError:
+        print("Error: QwenImageEditPlusPipeline not found.")
+        print("Make sure you have the latest diffusers: pip install -U diffusers")
+        sys.exit(1)
+
+    print(f"Loading model: {args.model}")
+    print(f"Device: {device}")
+
+    torch_dtype = torch.bfloat16 if device == "cuda" else torch.float32
+
+    try:
+        pipeline = pipeline_class.from_pretrained(
+            args.model,
+            torch_dtype=torch_dtype
+        )
+        pipeline.to(device)
+        pipeline.set_progress_bar_config(disable=False)
+    except Exception as e:
+        print(f"Error loading model: {e}")
+        sys.exit(1)
+
+    # Find images
+    formats = ["jpg", "jpeg", "png", "webp", "bmp", "tiff"]
+    image_files = get_image_files(input_dir, formats)
+
+    if not image_files:
+        print(f"No images found in '{input_dir}'")
+        sys.exit(0)
+
+    print(f"Found {len(image_files)} images")
+    print(f"Prompt: {args.prompt}")
+    print(f"Steps: {args.steps}, CFG: {args.cfg_scale}, True CFG: {args.true_cfg_scale}")
+    print("-" * 50)
+
+    processed = 0
+
+    for img_path in image_files:
+        try:
+            image = Image.open(img_path).convert("RGB")
+
+            # Set up generation parameters
+            gen_kwargs = {
+                "image": [image],
+                "prompt": args.prompt,
+                "negative_prompt": args.negative_prompt,
+                "num_inference_steps": args.steps,
+                "guidance_scale": args.cfg_scale,
+                "true_cfg_scale": args.true_cfg_scale,
+                "num_images_per_prompt": args.num_images,
+            }
+
+            # Add seed if specified
+            if args.seed is not None:
+                gen_kwargs["generator"] = torch.manual_seed(args.seed)
+
+            with torch.inference_mode():
+                output = pipeline(**gen_kwargs)
+
+            # Save output image(s)
+            for idx, out_img in enumerate(output.images):
+                if args.num_images > 1:
+                    out_name = f"{img_path.stem}_{idx + 1}.png"
+                else:
+                    out_name = f"{img_path.stem}.png"
+
+                out_path = output_dir / out_name
+                out_img.save(out_path)
+
+            print(f"[OK] {img_path.name} -> {len(output.images)} image(s)")
+            processed += 1
+
+        except Exception as e:
+            print(f"[ERROR] {img_path.name}: {e}")
+
+    print("-" * 50)
+    print(f"Done! Processed: {processed} images")
+
+
 def main():
     parser = argparse.ArgumentParser(
         prog="datasety",
@@ -379,6 +488,74 @@ def main():
     )
     caption_parser.set_defaults(func=cmd_caption)
 
+    # === SYNTHETIC command ===
+    synthetic_parser = subparsers.add_parser(
+        "synthetic",
+        help="Generate synthetic images using image editing models"
+    )
+    synthetic_parser.add_argument(
+        "--input", "-i",
+        required=True,
+        help="Input directory containing images"
+    )
+    synthetic_parser.add_argument(
+        "--output", "-o",
+        required=True,
+        help="Output directory for generated images"
+    )
+    synthetic_parser.add_argument(
+        "--prompt", "-p",
+        required=True,
+        help="Edit prompt (e.g., 'add a winter hat to the person')"
+    )
+    synthetic_parser.add_argument(
+        "--model",
+        default="Qwen/Qwen-Image-Edit-2511",
+        help="Model to use (default: Qwen/Qwen-Image-Edit-2511)"
+    )
+    synthetic_parser.add_argument(
+        "--device",
+        choices=["cpu", "cuda"],
+        default="cuda",
+        help="Device to run model on (default: cuda)"
+    )
+    synthetic_parser.add_argument(
+        "--steps",
+        type=int,
+        default=40,
+        help="Number of inference steps (default: 40)"
+    )
+    synthetic_parser.add_argument(
+        "--cfg-scale",
+        type=float,
+        default=1.0,
+        help="Guidance scale (default: 1.0)"
+    )
+    synthetic_parser.add_argument(
+        "--true-cfg-scale",
+        type=float,
+        default=4.0,
+        help="True CFG scale (default: 4.0)"
+    )
+    synthetic_parser.add_argument(
+        "--negative-prompt",
+        default=" ",
+        help="Negative prompt (default: ' ')"
+    )
+    synthetic_parser.add_argument(
+        "--num-images",
+        type=int,
+        default=1,
+        help="Number of images to generate per input (default: 1)"
+    )
+    synthetic_parser.add_argument(
+        "--seed",
+        type=int,
+        default=None,
+        help="Random seed for reproducibility"
+    )
+    synthetic_parser.set_defaults(func=cmd_synthetic)
+
     # Parse and execute
     args = parser.parse_args()
     args.func(args)

{datasety-0.1.0.dist-info → datasety-0.2.0.dist-info}/METADATA

@@ -1,14 +1,14 @@
 Metadata-Version: 2.4
 Name: datasety
-Version: 0.1.0
-Summary: CLI tool for dataset preparation: image resizing and captioning with Florence-2
+Version: 0.2.0
+Summary: CLI tool for dataset preparation: resize, caption, and synthetic image generation
 Project-URL: Homepage, https://github.com/kontextox/datasety
 Project-URL: Repository, https://github.com/kontextox/datasety
 Project-URL: Issues, https://github.com/kontextox/datasety/issues
 Author: kontextox
 License-Expression: MIT
 License-File: LICENSE
-Keywords: captioning,cli,dataset,florence-2,image-processing,machine-learning
+Keywords: captioning,cli,dataset,diffusers,florence-2,image-editing,image-processing,machine-learning,synthetic
 Classifier: Development Status :: 4 - Beta
 Classifier: Environment :: Console
 Classifier: Intended Audience :: Developers
@@ -23,6 +23,15 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Classifier: Topic :: Scientific/Engineering :: Image Processing
 Requires-Python: >=3.10
 Requires-Dist: pillow>=9.0.0
+Provides-Extra: all
+Requires-Dist: accelerate; extra == 'all'
+Requires-Dist: diffusers>=0.32.0; extra == 'all'
+Requires-Dist: einops; extra == 'all'
+Requires-Dist: sentencepiece; extra == 'all'
+Requires-Dist: timm; extra == 'all'
+Requires-Dist: torch>=2.0.0; extra == 'all'
+Requires-Dist: transformers<4.46.0,>=4.38.0; extra == 'all'
+Requires-Dist: transformers>=4.38.0; extra == 'all'
 Provides-Extra: caption
 Requires-Dist: einops; extra == 'caption'
 Requires-Dist: timm; extra == 'caption'
@@ -31,11 +40,17 @@ Requires-Dist: transformers<4.46.0,>=4.38.0; extra == 'caption'
 Provides-Extra: dev
 Requires-Dist: pytest>=7.0.0; extra == 'dev'
 Requires-Dist: ruff>=0.1.0; extra == 'dev'
+Provides-Extra: synthetic
+Requires-Dist: accelerate; extra == 'synthetic'
+Requires-Dist: diffusers>=0.32.0; extra == 'synthetic'
+Requires-Dist: sentencepiece; extra == 'synthetic'
+Requires-Dist: torch>=2.0.0; extra == 'synthetic'
+Requires-Dist: transformers>=4.38.0; extra == 'synthetic'
 Description-Content-Type: text/markdown
 
 # datasety
 
-CLI tool for dataset preparation: image resizing and captioning with Florence-2.
+CLI tool for dataset preparation: resize, caption, and synthetic image generation.
 
 ## Installation
 
@@ -43,10 +58,12 @@ CLI tool for dataset preparation: image resizing and captioning with Florence-2.
 pip install datasety
 ```
 
-For captioning support (requires PyTorch and Transformers):
+Install with specific features:
 
 ```bash
-pip install datasety[caption]
+pip install datasety[caption]     # Florence-2 captioning
+pip install datasety[synthetic]   # Qwen image editing
+pip install datasety[all]         # All features
 ```
 
 ## Usage
@@ -88,7 +105,7 @@ datasety resize \
 1. Finds all images matching input formats
 2. Skips images where either dimension is smaller than target
 3. Resizes proportionally so the smaller side matches target
-4. Crops from the specified area to exact dimensions
+4. Crops from the specified position to exact dimensions
 5. Saves with high quality (95% for jpg/webp)
 
 ### Generate Captions
@@ -130,6 +147,43 @@ datasety caption \
 
 This creates a `.txt` file for each image with the generated caption.
 
+### Generate Synthetic Images
+
+Generate synthetic variations of images using Qwen-Image-Edit:
+
+```bash
+datasety synthetic --input ./images --output ./synthetic --prompt "add a winter hat"
+```
+
+**Options:**
+
+| Option              | Description                       | Default                    |
+| ------------------- | --------------------------------- | -------------------------- |
+| `--input`, `-i`     | Input directory                   | (required)                 |
+| `--output`, `-o`    | Output directory                  | (required)                 |
+| `--prompt`, `-p`    | Edit prompt                       | (required)                 |
+| `--model`           | Model to use                      | `Qwen/Qwen-Image-Edit-2511`|
+| `--device`          | `cpu` or `cuda`                   | `cuda`                     |
+| `--steps`           | Number of inference steps         | `40`                       |
+| `--cfg-scale`       | Guidance scale                    | `1.0`                      |
+| `--true-cfg-scale`  | True CFG scale                    | `4.0`                      |
+| `--negative-prompt` | Negative prompt                   | `" "`                      |
+| `--num-images`      | Images to generate per input      | `1`                        |
+| `--seed`            | Random seed for reproducibility   | (random)                   |
+
+**Example:**
+
+```bash
+datasety synthetic \
+    --input ./dataset \
+    --output ./synthetic \
+    --prompt "add sunglasses to the person, keep everything else the same" \
+    --device cuda \
+    --steps 40 \
+    --true-cfg-scale 4.0 \
+    --seed 42
+```
+
 ## Common Workflows
 
 ### Prepare a LoRA Training Dataset
@@ -142,6 +196,18 @@ datasety resize -i ./raw -o ./dataset -r 1024x1024 --crop-position center
 datasety caption -i ./dataset -o ./dataset --trigger-word "[trigger]" --device cuda
 ```
 
+### Augment Dataset with Synthetic Variations
+
+```bash
+# Generate variations with different accessories
+datasety synthetic \
+    -i ./dataset \
+    -o ./synthetic \
+    --prompt "add a red scarf" \
+    --num-images 2 \
+    --device cuda
+```
+
 ### Batch Process with Numbered Files
 
 ```bash
@@ -157,7 +223,8 @@ datasety resize \
 
 - Python 3.10+
 - Pillow (for resize)
-- PyTorch + Transformers (for caption, install with `pip install datasety[caption]`)
+- PyTorch + Transformers (for caption: `pip install datasety[caption]`)
+- PyTorch + Diffusers (for synthetic: `pip install datasety[synthetic]`)
 
 ## License
 

datasety-0.2.0.dist-info/RECORD

@@ -0,0 +1,8 @@
+datasety/__init__.py,sha256=rApR3JxIHU0q1LJ8_k_oM-5alQO0mW-4Ac9-GH5HmhA,105
+datasety/__main__.py,sha256=rhdW0XGNAX-GC5IqU62ulCVccf3kgelddrGghYMZzn4,115
+datasety/cli.py,sha256=lI18ORKHQdiZdIJ5icr3lo4YS8divLp8tz8yrrhtkF4,17807
+datasety-0.2.0.dist-info/METADATA,sha256=xmi3GjI3mNVgu-tvls6HUA8yM8Wrsul6IcuZjK0xqGo,8170
+datasety-0.2.0.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+datasety-0.2.0.dist-info/entry_points.txt,sha256=oWbVHN1_qyuWezjxuhsAGAqqwmivRUtG2jCYKm8bVnE,47
+datasety-0.2.0.dist-info/licenses/LICENSE,sha256=dUhuoK-TCRQMpuLEAdfme-qPSJI0TlcH9jlNxeg9_EQ,1056
+datasety-0.2.0.dist-info/RECORD,,

datasety-0.1.0.dist-info/RECORD

@@ -1,9 +0,0 @@
-datasety/__init__.py,sha256=LeNjBou33I9yomQhLmpfZWXEJeW2Io9ZvHnZmYXltQ4,105
-datasety/__main__.py,sha256=rhdW0XGNAX-GC5IqU62ulCVccf3kgelddrGghYMZzn4,115
-datasety/cli.py,sha256=K5doc2QZBLKDS3MjVkTsGe4giz31eo6xMCx8G4wdBEM,12399
-datasety/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-datasety-0.1.0.dist-info/METADATA,sha256=u-9NanmOw3QZ3pWI1VNmrUG8CBAjFwyCnVVY_I6TpSE,5429
-datasety-0.1.0.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-datasety-0.1.0.dist-info/entry_points.txt,sha256=oWbVHN1_qyuWezjxuhsAGAqqwmivRUtG2jCYKm8bVnE,47
-datasety-0.1.0.dist-info/licenses/LICENSE,sha256=dUhuoK-TCRQMpuLEAdfme-qPSJI0TlcH9jlNxeg9_EQ,1056
-datasety-0.1.0.dist-info/RECORD,,