diffusers-workflow 0.4.0a3__tar.gz

diffusers_workflow-0.4.0a3/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

diffusers_workflow-0.4.0a3/MANIFEST.in

@@ -0,0 +1,3 @@
+include dw/*.json
+recursive-include dw/workflows *.json
+recursive-include dw/server/ui *

diffusers_workflow-0.4.0a3/PKG-INFO

@@ -0,0 +1,310 @@
+Metadata-Version: 2.4
+Name: diffusers-workflow
+Version: 0.4.0a3
+Summary: Declarative workflow engine and web UI for Hugging Face Diffusers
+Author: dkackman
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/dkackman/diffusers-workflow
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: torch>=2.0.0
+Requires-Dist: diffusers
+Requires-Dist: transformers
+Requires-Dist: accelerate
+Requires-Dist: huggingface_hub
+Requires-Dist: numpy
+Requires-Dist: Pillow
+Requires-Dist: av
+Requires-Dist: qrcode
+Requires-Dist: jsonschema
+Requires-Dist: concurrent-log-handler
+Requires-Dist: controlnet-aux
+Requires-Dist: soundfile
+Provides-Extra: server
+Requires-Dist: fastapi; extra == "server"
+Requires-Dist: uvicorn[standard]; extra == "server"
+Provides-Extra: dev
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: pytest-cov; extra == "dev"
+Requires-Dist: black; extra == "dev"
+Requires-Dist: flake8; extra == "dev"
+Requires-Dist: build; extra == "dev"
+Dynamic: license-file
+
+[![CodeQL](https://github.com/dkackman/diffusers-workflow/actions/workflows/github-code-scanning/codeql/badge.svg)](https://github.com/dkackman/diffusers-workflow/actions/workflows/github-code-scanning/codeql)
+
+# diffusers-workflow
+
+A declarative workflow engine and web UI for the [Hugging Face Diffusers library](https://github.com/huggingface/diffusers). Define image/video generation pipelines in JSON — with full access to the configuration diffusers exposes — and run them from the command line, an interactive REPL, or a browser.
+
+**Python 3.10-3.14 | CUDA (NVIDIA) | MPS (Apple Silicon) | CPU**
+
+<picture>
+  <source media="(prefers-color-scheme: dark)" srcset="docs/img/ui-workflows-dark.png">
+  <img alt="The workflow browser: every workflow as a card with its description, output kinds, and variables" src="docs/img/ui-workflows.png">
+</picture>
+
+## Features
+
+- **Web UI** — browse and run workflows, edit them in introspection-driven forms, watch jobs stream live progress, manage generated output and the models on disk. `python -m dw.serve` and open a browser. See [Server & Web UI](docs/SERVER.md).
+- **Declarative JSON workflows** with variable substitution and cross-step data flow
+- **Multi-step pipelines** — chain text-to-image, image-to-video, inpainting, ControlNet
+- **Reproducible by construction** — outputs embed their full workflow definition and seed; any image in the gallery reopens as the exact workflow that made it
+- **Long-video chaining** — run a video pipeline once per segment and stitch the segments into one clip, with audio-driven length and frame-to-frame continuity
+- **Quantization** — BitsAndBytes, TorchAO, GGUF, SDNQ, optimum-quanto
+- **Inference acceleration** — TeaCache, FirstBlockCache, FasterCache, MagCache, TaylorSeerCache
+- **Prompt weighting** — A1111-style `(word:1.5)` syntax with long prompt support
+- **LoRA and IP-Adapter** support
+- **Composable workflows** from multiple JSON files with `builtin:` references
+- **Utility tasks** — upscaling, face restoration, segmentation, captioning, frame interpolation, QR codes, and more
+- **Interactive REPL** with persistent GPU model caching (2-4x faster iteration)
+- **Cross-platform** — CUDA, MPS (Apple Silicon), and CPU
+
+## Installation
+
+### Linux / macOS
+
+```bash
+bash ./install.sh
+source ./activate
+python -m dw.test
+```
+
+### Windows
+
+```powershell
+.\install.ps1
+.\venv\scripts\activate
+python -m dw.test
+```
+
+The install scripts detect your Python version, create a virtual environment, and install all dependencies including platform-specific packages (bitsandbytes on CUDA, fp4-fp8-for-torch-mps on macOS).
+
+## The Web UI
+
+```bash
+python -m dw.serve
+# diffusers-workflow server on http://127.0.0.1:8765
+```
+
+Everything the engine does, in a browser backed by a persistent GPU worker — models stay loaded between runs.
+
+**A form-based editor with the real pipeline signatures.** Forms and argument autocomplete are generated by introspecting diffusers itself, so every knob a pipeline exposes is available — with its documentation — without leaving the browser. A split view puts the JSON beside the form, both editable; validation catches schema errors *and* argument typos (by checking the pipeline's actual call signature) before any model loads.
+
+![The editor: introspection-driven forms beside live JSON in Monaco](docs/img/ui-editor.png)
+
+**A gallery where every image is a recipe.** Outputs embed their workflow and seed; *open as workflow* drops the definition into the editor with the seed pinned, ready to reproduce or riff on.
+
+![The gallery with generated images and videos](docs/img/ui-gallery.jpg)
+
+**A model manager for the disk your models actually consume.** The Hugging Face hub cache, inventoried: sizes, revisions, last-used dates, free space — download new models by id with live progress, delete with one click.
+
+![The model manager listing cached models with sizes](docs/img/ui-models.png)
+
+Jobs queue, stream progress live (per denoising step), cancel cooperatively, and persist to a searchable history. See [Server & Web UI](docs/SERVER.md) for the pages and the HTTP API.
+
+## Usage
+
+### Run a Workflow
+
+```bash
+python -m dw.run examples/flux/FluxDev.json
+python -m dw.run examples/flux/FluxDev.json prompt="a cat" num_images_per_prompt=4
+```
+
+### Validate a Workflow
+
+```bash
+python -m dw.validate examples/flux/FluxDev.json
+```
+
+### Interactive REPL
+
+```bash
+python -m dw.repl
+```
+
+```text
+dw> workflow load flux/FluxDev
+dw> arg set prompt="a beautiful sunset"
+dw> workflow run
+[... models load once ...]
+
+dw> arg set prompt="a starry night"
+dw> workflow run
+Reusing loaded models from cache
+[... 2-4x faster ...]
+
+dw> memory show
+dw> ?               # show all command groups
+```
+
+See [REPL Commands](docs/REPL_COMMANDS.md) and [Worker Guide](docs/REPL_WORKER_GUIDE.md).
+
+## Workflow Examples
+
+### Simple Image Generation
+
+```json
+{
+    "id": "flux_example",
+    "variables": {
+        "prompt": "an apple",
+        "num_images_per_prompt": 1
+    },
+    "steps": [
+        {
+            "name": "main",
+            "pipeline": {
+                "configuration": {
+                    "component_type": "FluxPipeline",
+                    "offload": "sequential"
+                },
+                "from_pretrained_arguments": {
+                    "model_name": "black-forest-labs/FLUX.1-dev",
+                    "torch_dtype": "torch.bfloat16"
+                },
+                "arguments": {
+                    "prompt": "variable:prompt",
+                    "num_inference_steps": 25,
+                    "num_images_per_prompt": "variable:num_images_per_prompt",
+                    "guidance_scale": 3.5
+                }
+            },
+            "result": {
+                "content_type": "image/jpeg"
+            }
+        }
+    ]
+}
+```
+
+Override variables from the command line:
+
+```bash
+python -m dw.run flux_example.json prompt="an orange" num_images_per_prompt=4
+```
+
+### Multi-Step Workflow (Image to Video)
+
+Chain steps using `previous_result:step_name` to pass outputs between steps:
+
+```json
+{
+    "id": "img2vid",
+    "steps": [
+        {
+            "name": "image_generation",
+            "pipeline": {
+                "configuration": {
+                    "component_type": "StableDiffusion3Pipeline",
+                    "offload": "model"
+                },
+                "from_pretrained_arguments": {
+                    "model_name": "stabilityai/stable-diffusion-3.5-large",
+                    "torch_dtype": "torch.bfloat16"
+                },
+                "arguments": {
+                    "prompt": "a luminous owl in a neon forest",
+                    "num_inference_steps": 25,
+                    "guidance_scale": 4.5
+                }
+            },
+            "result": { "content_type": "image/png" }
+        },
+        {
+            "name": "video",
+            "pipeline": {
+                "configuration": {
+                    "component_type": "CogVideoXImageToVideoPipeline",
+                    "offload": "sequential",
+                    "vae": { "configuration": { "enable_slicing": true, "enable_tiling": true } }
+                },
+                "from_pretrained_arguments": {
+                    "model_name": "THUDM/CogVideoX-5b-I2V",
+                    "torch_dtype": "torch.bfloat16"
+                },
+                "arguments": {
+                    "image": "previous_result:image_generation",
+                    "prompt": "The owl blinks slowly",
+                    "num_inference_steps": 50,
+                    "num_frames": 49,
+                    "guidance_scale": 6
+                }
+            },
+            "result": { "content_type": "video/mp4" }
+        }
+    ]
+}
+```
+
+### Inference Acceleration
+
+Speed up generation with built-in diffusers caching or TeaCache:
+
+```json
+"configuration": {
+    "component_type": "FluxPipeline",
+    "cache": { "type": "first_block", "threshold": 0.05 }
+}
+```
+
+```json
+"configuration": {
+    "component_type": "FluxPipeline",
+    "teacache": { "rel_l1_thresh": 0.6 }
+}
+```
+
+### Prompt Weighting
+
+Use A1111-style syntax for per-token weighting:
+
+```json
+"configuration": {
+    "component_type": "FluxPipeline",
+    "prompt_weighting": true
+}
+```
+
+```text
+a (photorealistic:1.4) portrait with (bright red hair:1.3) and [freckles]
+```
+
+## JSON Schema
+
+**Interactive schema browser:** [View Schema](https://json-schema.app/view/%23?url=https%3A%2F%2Fraw.githubusercontent.com%2Fdkackman%2Fdiffusers-workflow%2Frefs%2Fheads%2Fmaster%2Fdw%2Fworkflow_schema.json)
+
+See [examples/](examples/) for more workflow files.
+
+## Documentation
+
+### Guides
+
+- [Server & Web UI](docs/SERVER.md) — The web UI, jobs API, and introspection service
+- [Workflow Guide](docs/WORKFLOW_GUIDE.md) — JSON structure, variables, steps, data flow
+- [Quantization](docs/QUANTIZATION.md) — BitsAndBytes, TorchAO, GGUF, SDNQ
+- [Inference Acceleration](docs/ACCELERATION.md) — torch.compile, FirstBlockCache, MagCache, TaylorSeer, TeaCache
+- [Fast on 24GB](docs/RECIPES_24GB.md) — Recommended speed/memory configurations per model family
+- [LoRA](docs/LORAS.md) — Loading and stacking LoRA adapters
+- [IP-Adapter](docs/IP_ADAPTER.md) — Image-prompt conditioning
+- [Prompt Weighting](docs/PROMPT_WEIGHTING.md) — A1111-style syntax
+- [Tasks](docs/TASKS.md) — Image processing, ControlNet preprocessors, utilities
+
+### Reference
+
+- [REPL Commands](docs/REPL_COMMANDS.md) — Interactive REPL command reference
+- [Worker Guide](docs/REPL_WORKER_GUIDE.md) — GPU persistence and troubleshooting
+- [Dependencies](docs/DEPENDENCIES.md) — Installation details
+- [Security](docs/SECURITY.md) — Security model
+- [Testing](docs/TESTING.md) — Running the test suite
+- [Releasing](docs/RELEASING.md) — Cutting a release from a version tag