abstractvision 0.1.0__tar.gz → 0.2.1__tar.gz

abstractvision-0.2.1/PKG-INFO

@@ -0,0 +1,243 @@
+Metadata-Version: 2.4
+Name: abstractvision
+Version: 0.2.1
+Summary: Model-agnostic generative vision abstractions (image/video) for the Abstract ecosystem
+Author-email: Laurent-Philippe Albou <contact@abstractcore.ai>
+License: MIT
+Project-URL: Homepage, https://github.com/abstractcore/abstractvision
+Project-URL: Repository, https://github.com/abstractcore/abstractvision
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Topic :: Multimedia
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: diffusers>=0.36.0
+Requires-Dist: torch<3.0.0,>=2.0
+Requires-Dist: transformers<6.0.0,>=4.0
+Requires-Dist: accelerate>=0.0
+Requires-Dist: safetensors>=0.0
+Requires-Dist: sentencepiece>=0.1.99
+Requires-Dist: protobuf>=3.20.0
+Requires-Dist: einops>=0.7.0
+Requires-Dist: peft>=0.10.0
+Requires-Dist: Pillow>=9.0
+Requires-Dist: stable-diffusion-cpp-python>=0.4.2
+Provides-Extra: openai-compatible
+Provides-Extra: sdcpp
+Requires-Dist: stable-diffusion-cpp-python>=0.4.2; extra == "sdcpp"
+Provides-Extra: huggingface
+Requires-Dist: diffusers>=0.36.0; extra == "huggingface"
+Requires-Dist: torch>=2.0; extra == "huggingface"
+Requires-Dist: transformers>=4.0; extra == "huggingface"
+Requires-Dist: accelerate>=0.0; extra == "huggingface"
+Requires-Dist: safetensors>=0.0; extra == "huggingface"
+Requires-Dist: Pillow>=9.0; extra == "huggingface"
+Provides-Extra: local
+Requires-Dist: stable-diffusion-cpp-python>=0.4.2; extra == "local"
+Requires-Dist: diffusers>=0.36.0; extra == "local"
+Requires-Dist: torch>=2.0; extra == "local"
+Requires-Dist: transformers>=4.0; extra == "local"
+Requires-Dist: accelerate>=0.0; extra == "local"
+Requires-Dist: safetensors>=0.0; extra == "local"
+Requires-Dist: Pillow>=9.0; extra == "local"
+Provides-Extra: huggingface-dev
+Requires-Dist: diffusers>=0.36.0; extra == "huggingface-dev"
+Requires-Dist: torch>=2.0; extra == "huggingface-dev"
+Requires-Dist: transformers>=5.0; extra == "huggingface-dev"
+Requires-Dist: accelerate>=0.0; extra == "huggingface-dev"
+Requires-Dist: safetensors>=0.0; extra == "huggingface-dev"
+Requires-Dist: Pillow>=9.0; extra == "huggingface-dev"
+Provides-Extra: abstractcore
+Requires-Dist: abstractcore>=2.0.0; extra == "abstractcore"
+Dynamic: license-file
+
+# AbstractVision
+
+Model-agnostic generative vision API (images, optional video) for Python and the Abstract* ecosystem.
+
+## What you get
+
+- A stable task API: `VisionManager` (`src/abstractvision/vision_manager.py`)
+- A packaged capability registry (“what models can do”): `VisionModelCapabilitiesRegistry` backed by `src/abstractvision/assets/vision_model_capabilities.json`
+- Optional artifact-ref outputs (small JSON refs): `LocalAssetStore` / store adapters (`src/abstractvision/artifacts.py`)
+- Built-in backends (`src/abstractvision/backends/`):
+  - OpenAI-compatible HTTP (`openai_compatible.py`)
+  - Local Diffusers (`huggingface_diffusers.py`)
+  - Local stable-diffusion.cpp / GGUF (`stable_diffusion_cpp.py`)
+- CLI/REPL for manual testing: `abstractvision ...` (`src/abstractvision/cli.py`)
+
+## Status (current backend support)
+
+- Built-in backends implement: `text_to_image` and `image_to_image`.
+- Video (`text_to_video`, `image_to_video`) is supported only via the OpenAI-compatible backend **when** endpoints are configured.
+- `multi_view_image` is part of the public API (`VisionManager.generate_angles`) but no built-in backend implements it yet.
+
+Details: `docs/reference/backends.md`.
+
+## Installation
+
+```bash
+pip install abstractvision
+```
+
+Install optional integrations:
+
+```bash
+pip install "abstractvision[abstractcore]"
+```
+
+Some newer model pipelines may require Diffusers from GitHub `main` (see `docs/getting-started.md`):
+
+```bash
+pip install -U "abstractvision[huggingface-dev]"
+```
+
+For local dev (from a repo checkout):
+
+```bash
+pip install -e .
+```
+
+## Usage
+
+Start here:
+- Getting started: `docs/getting-started.md`
+- FAQ: `docs/faq.md`
+- API reference: `docs/api.md`
+- Architecture: `docs/architecture.md`
+- Docs index: `docs/README.md`
+
+### Capability-driven model selection
+
+```python
+from abstractvision import VisionModelCapabilitiesRegistry
+
+reg = VisionModelCapabilitiesRegistry()
+assert reg.supports("Qwen/Qwen-Image-2512", "text_to_image")
+
+print(reg.list_tasks())
+print(reg.models_for_task("text_to_image"))
+```
+
+### Backend wiring + generation (artifact outputs)
+
+The default install is “batteries included” (Torch + Diffusers + stable-diffusion.cpp python bindings), but heavy
+modules are imported lazily (see `src/abstractvision/backends/__init__.py`).
+
+```python
+from abstractvision import LocalAssetStore, VisionManager, VisionModelCapabilitiesRegistry, is_artifact_ref
+from abstractvision.backends import OpenAICompatibleBackendConfig, OpenAICompatibleVisionBackend
+
+reg = VisionModelCapabilitiesRegistry()
+
+backend = OpenAICompatibleVisionBackend(
+    config=OpenAICompatibleBackendConfig(
+        base_url="http://localhost:1234/v1",
+        api_key="YOUR_KEY",      # optional for local servers
+        model_id="REMOTE_MODEL", # optional (server-dependent)
+    )
+)
+
+vm = VisionManager(
+    backend=backend,
+    store=LocalAssetStore(),         # enables artifact-ref outputs
+    model_id="zai-org/GLM-Image",    # optional: capability gating
+    registry=reg,                   # optional: reuse loaded registry
+)
+
+out = vm.generate_image("a cinematic photo of a red fox in snow")
+assert is_artifact_ref(out)
+print(out)  # {"$artifact": "...", "content_type": "...", ...}
+
+png_bytes = vm.store.load_bytes(out["$artifact"])  # type: ignore[union-attr]
+```
+
+### Interactive testing (CLI / REPL)
+
+```bash
+abstractvision models
+abstractvision tasks
+abstractvision show-model zai-org/GLM-Image
+
+abstractvision repl
+```
+
+Inside the REPL:
+
+```text
+/backend openai http://localhost:1234/v1
+/cap-model zai-org/GLM-Image
+/set width 1024
+/set height 1024
+/t2i "a watercolor painting of a lighthouse" --open
+```
+
+The CLI/REPL can also be configured via `ABSTRACTVISION_*` env vars; see `docs/reference/configuration.md`.
+
+One-shot commands (OpenAI-compatible HTTP backend only):
+
+```bash
+abstractvision t2i --base-url http://localhost:1234/v1 "a studio photo of an espresso machine"
+abstractvision i2i --base-url http://localhost:1234/v1 --image ./input.png "make it watercolor"
+```
+
+#### Local GGUF via stable-diffusion.cpp
+
+If you want to run GGUF diffusion models locally (e.g. Qwen Image), use the stable-diffusion.cpp backend (`sdcpp`).
+
+Recommended (pip-only; no external binary download): `pip install abstractvision` already includes the stable-diffusion.cpp python bindings (`stable-diffusion-cpp-python`).
+
+Alternative (external executable):
+
+- Install `sd-cli`: https://github.com/leejet/stable-diffusion.cpp/releases
+
+In the REPL:
+
+```text
+/backend sdcpp /path/to/qwen-image-2512-Q4_K_M.gguf /path/to/qwen_image_vae.safetensors /path/to/Qwen2.5-VL-7B-Instruct-*.gguf
+/t2i "a watercolor painting of a lighthouse" --sampling-method euler --offload-to-cpu --diffusion-fa --flow-shift 3 --open
+```
+
+Extra flags are forwarded via `request.extra`. In CLI mode they are forwarded to `sd-cli`; in python bindings mode, keys are mapped to python binding kwargs when supported and unsupported keys are ignored.
+
+### AbstractCore tool integration (artifact refs)
+
+If you’re using AbstractCore tool calling, AbstractVision can expose vision tasks as tools:
+
+```python
+from abstractvision.integrations.abstractcore import make_vision_tools
+
+tools = make_vision_tools(vision_manager=vm, model_id="zai-org/GLM-Image")
+```
+
+## Project
+
+- Release notes: `CHANGELOG.md`
+- Contributing: `CONTRIBUTING.md`
+- Security: `SECURITY.md`
+- Acknowledgments: `ACKNOWLEDMENTS.md`
+
+## Requirements
+
+- Python >= 3.8
+
+## License
+
+MIT License - see LICENSE file for details.
+
+## Author
+
+Laurent-Philippe Albou
+
+## Contact
+
+contact@abstractcore.ai

abstractvision-0.2.1/README.md

@@ -0,0 +1,181 @@
+# AbstractVision
+
+Model-agnostic generative vision API (images, optional video) for Python and the Abstract* ecosystem.
+
+## What you get
+
+- A stable task API: `VisionManager` (`src/abstractvision/vision_manager.py`)
+- A packaged capability registry (“what models can do”): `VisionModelCapabilitiesRegistry` backed by `src/abstractvision/assets/vision_model_capabilities.json`
+- Optional artifact-ref outputs (small JSON refs): `LocalAssetStore` / store adapters (`src/abstractvision/artifacts.py`)
+- Built-in backends (`src/abstractvision/backends/`):
+  - OpenAI-compatible HTTP (`openai_compatible.py`)
+  - Local Diffusers (`huggingface_diffusers.py`)
+  - Local stable-diffusion.cpp / GGUF (`stable_diffusion_cpp.py`)
+- CLI/REPL for manual testing: `abstractvision ...` (`src/abstractvision/cli.py`)
+
+## Status (current backend support)
+
+- Built-in backends implement: `text_to_image` and `image_to_image`.
+- Video (`text_to_video`, `image_to_video`) is supported only via the OpenAI-compatible backend **when** endpoints are configured.
+- `multi_view_image` is part of the public API (`VisionManager.generate_angles`) but no built-in backend implements it yet.
+
+Details: `docs/reference/backends.md`.
+
+## Installation
+
+```bash
+pip install abstractvision
+```
+
+Install optional integrations:
+
+```bash
+pip install "abstractvision[abstractcore]"
+```
+
+Some newer model pipelines may require Diffusers from GitHub `main` (see `docs/getting-started.md`):
+
+```bash
+pip install -U "abstractvision[huggingface-dev]"
+```
+
+For local dev (from a repo checkout):
+
+```bash
+pip install -e .
+```
+
+## Usage
+
+Start here:
+- Getting started: `docs/getting-started.md`
+- FAQ: `docs/faq.md`
+- API reference: `docs/api.md`
+- Architecture: `docs/architecture.md`
+- Docs index: `docs/README.md`
+
+### Capability-driven model selection
+
+```python
+from abstractvision import VisionModelCapabilitiesRegistry
+
+reg = VisionModelCapabilitiesRegistry()
+assert reg.supports("Qwen/Qwen-Image-2512", "text_to_image")
+
+print(reg.list_tasks())
+print(reg.models_for_task("text_to_image"))
+```
+
+### Backend wiring + generation (artifact outputs)
+
+The default install is “batteries included” (Torch + Diffusers + stable-diffusion.cpp python bindings), but heavy
+modules are imported lazily (see `src/abstractvision/backends/__init__.py`).
+
+```python
+from abstractvision import LocalAssetStore, VisionManager, VisionModelCapabilitiesRegistry, is_artifact_ref
+from abstractvision.backends import OpenAICompatibleBackendConfig, OpenAICompatibleVisionBackend
+
+reg = VisionModelCapabilitiesRegistry()
+
+backend = OpenAICompatibleVisionBackend(
+    config=OpenAICompatibleBackendConfig(
+        base_url="http://localhost:1234/v1",
+        api_key="YOUR_KEY",      # optional for local servers
+        model_id="REMOTE_MODEL", # optional (server-dependent)
+    )
+)
+
+vm = VisionManager(
+    backend=backend,
+    store=LocalAssetStore(),         # enables artifact-ref outputs
+    model_id="zai-org/GLM-Image",    # optional: capability gating
+    registry=reg,                   # optional: reuse loaded registry
+)
+
+out = vm.generate_image("a cinematic photo of a red fox in snow")
+assert is_artifact_ref(out)
+print(out)  # {"$artifact": "...", "content_type": "...", ...}
+
+png_bytes = vm.store.load_bytes(out["$artifact"])  # type: ignore[union-attr]
+```
+
+### Interactive testing (CLI / REPL)
+
+```bash
+abstractvision models
+abstractvision tasks
+abstractvision show-model zai-org/GLM-Image
+
+abstractvision repl
+```
+
+Inside the REPL:
+
+```text
+/backend openai http://localhost:1234/v1
+/cap-model zai-org/GLM-Image
+/set width 1024
+/set height 1024
+/t2i "a watercolor painting of a lighthouse" --open
+```
+
+The CLI/REPL can also be configured via `ABSTRACTVISION_*` env vars; see `docs/reference/configuration.md`.
+
+One-shot commands (OpenAI-compatible HTTP backend only):
+
+```bash
+abstractvision t2i --base-url http://localhost:1234/v1 "a studio photo of an espresso machine"
+abstractvision i2i --base-url http://localhost:1234/v1 --image ./input.png "make it watercolor"
+```
+
+#### Local GGUF via stable-diffusion.cpp
+
+If you want to run GGUF diffusion models locally (e.g. Qwen Image), use the stable-diffusion.cpp backend (`sdcpp`).
+
+Recommended (pip-only; no external binary download): `pip install abstractvision` already includes the stable-diffusion.cpp python bindings (`stable-diffusion-cpp-python`).
+
+Alternative (external executable):
+
+- Install `sd-cli`: https://github.com/leejet/stable-diffusion.cpp/releases
+
+In the REPL:
+
+```text
+/backend sdcpp /path/to/qwen-image-2512-Q4_K_M.gguf /path/to/qwen_image_vae.safetensors /path/to/Qwen2.5-VL-7B-Instruct-*.gguf
+/t2i "a watercolor painting of a lighthouse" --sampling-method euler --offload-to-cpu --diffusion-fa --flow-shift 3 --open
+```
+
+Extra flags are forwarded via `request.extra`. In CLI mode they are forwarded to `sd-cli`; in python bindings mode, keys are mapped to python binding kwargs when supported and unsupported keys are ignored.
+
+### AbstractCore tool integration (artifact refs)
+
+If you’re using AbstractCore tool calling, AbstractVision can expose vision tasks as tools:
+
+```python
+from abstractvision.integrations.abstractcore import make_vision_tools
+
+tools = make_vision_tools(vision_manager=vm, model_id="zai-org/GLM-Image")
+```
+
+## Project
+
+- Release notes: `CHANGELOG.md`
+- Contributing: `CONTRIBUTING.md`
+- Security: `SECURITY.md`
+- Acknowledgments: `ACKNOWLEDMENTS.md`
+
+## Requirements
+
+- Python >= 3.8
+
+## License
+
+MIT License - see LICENSE file for details.
+
+## Author
+
+Laurent-Philippe Albou
+
+## Contact
+
+contact@abstractcore.ai

abstractvision-0.2.1/pyproject.toml

@@ -0,0 +1,116 @@
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "abstractvision"
+dynamic = ["version"]
+description = "Model-agnostic generative vision abstractions (image/video) for the Abstract ecosystem"
+readme = "README.md"
+license = {text = "MIT"}
+authors = [{name = "Laurent-Philippe Albou", email = "contact@abstractcore.ai"}]
+requires-python = ">=3.8"
+classifiers = [
+  "Development Status :: 3 - Alpha",
+  "Intended Audience :: Developers",
+  "License :: OSI Approved :: MIT License",
+  "Operating System :: OS Independent",
+  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3.8",
+  "Programming Language :: Python :: 3.9",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+  "Topic :: Multimedia",
+  "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+# Batteries-included by default: users should only need to download model weights.
+# NOTE: This is intentionally heavy (torch + diffusers + stable-diffusion.cpp bindings).
+dependencies = [
+  "diffusers>=0.36.0",
+  "torch>=2.0,<3.0.0",
+  "transformers>=4.0,<6.0.0",
+  "accelerate>=0.0",
+  "safetensors>=0.0",
+  # Needed by T5 tokenizers used in SD3/FLUX and some other diffusion pipelines.
+  "sentencepiece>=0.1.99",
+  # Some HF tokenizers/pipelines require protobuf at runtime.
+  "protobuf>=3.20.0",
+  # Used by some modern diffusion architectures.
+  "einops>=0.7.0",
+  # LoRA adapter support in Diffusers.
+  "peft>=0.10.0",
+  "Pillow>=9.0",
+  "stable-diffusion-cpp-python>=0.4.2",
+]
+
+[project.urls]
+Homepage = "https://github.com/abstractcore/abstractvision"
+Repository = "https://github.com/abstractcore/abstractvision"
+
+[project.scripts]
+abstractvision = "abstractvision.cli:main"
+
+[project.entry-points."abstractcore.capabilities_plugins"]
+abstractvision = "abstractvision.integrations.abstractcore_plugin:register"
+
+[project.optional-dependencies]
+# OpenAI-compatible HTTP backend is stdlib-only today; keep the extra for forward compatibility.
+openai-compatible = []
+
+# Local generation via stable-diffusion.cpp python bindings (pip-installable).
+sdcpp = [
+  "stable-diffusion-cpp-python>=0.4.2",
+]
+
+# Local generation via Diffusers (heavy deps; opt-in).
+huggingface = [
+  "diffusers>=0.36.0",
+  "torch>=2.0",
+  "transformers>=4.0",
+  "accelerate>=0.0",
+  "safetensors>=0.0",
+  "Pillow>=9.0",
+]
+
+# Convenience: installs both local backends (Diffusers + stable-diffusion.cpp python bindings).
+local = [
+  "stable-diffusion-cpp-python>=0.4.2",
+  "diffusers>=0.36.0",
+  "torch>=2.0",
+  "transformers>=4.0",
+  "accelerate>=0.0",
+  "safetensors>=0.0",
+  "Pillow>=9.0",
+]
+
+# NOTE: PyPI rejects VCS/direct URL dependencies in package metadata.
+# If you need Diffusers "main" for unreleased pipelines, install it explicitly *after*:
+#   pip install "abstractvision[huggingface-dev]"
+#   pip install "diffusers @ git+https://github.com/huggingface/diffusers@main"
+huggingface-dev = [
+  "diffusers>=0.36.0",
+  "torch>=2.0",
+  "transformers>=5.0",
+  "accelerate>=0.0",
+  "safetensors>=0.0",
+  "Pillow>=9.0",
+]
+
+# Tool integration module (optional import). Kept optional to avoid circular deps with AbstractCore.
+abstractcore = ["abstractcore>=2.0.0"]
+
+[tool.setuptools]
+packages = [
+  "abstractvision",
+  "abstractvision.backends",
+  "abstractvision.integrations",
+]
+
+[tool.setuptools.package-dir]
+"" = "src"
+
+[tool.setuptools.dynamic]
+version = {attr = "abstractvision.__version__"}
+
+[tool.setuptools.package-data]
+abstractvision = ["assets/*.json"]

abstractvision-0.2.1/src/abstractvision/__init__.py

@@ -0,0 +1,22 @@
+"""abstractvision: Generative vision capabilities for abstractcore.ai.
+
+The default install is batteries-included (Diffusers + stable-diffusion.cpp python bindings),
+so users generally only need to download model weights.
+"""
+
+from .artifacts import LocalAssetStore, RuntimeArtifactStoreAdapter, is_artifact_ref
+from .model_capabilities import VisionModelCapabilitiesRegistry
+from .vision_manager import VisionManager
+
+__version__ = "0.2.1"
+__author__ = "Laurent-Philippe Albou"
+__email__ = "contact@abstractcore.ai"
+
+__all__ = [
+    "VisionManager",
+    "VisionModelCapabilitiesRegistry",
+    "LocalAssetStore",
+    "RuntimeArtifactStoreAdapter",
+    "is_artifact_ref",
+    "__version__",
+]

abstractvision-0.2.1/src/abstractvision/__main__.py

@@ -0,0 +1,8 @@
+from __future__ import annotations
+
+from .cli import main
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())
+