Spaces:
Running on Zero
Running on Zero
| title: Color Grade Transfer | |
| emoji: 😻 | |
| colorFrom: purple | |
| colorTo: blue | |
| sdk: gradio | |
| sdk_version: 6.17.3 | |
| python_version: '3.12' | |
| app_file: app.py | |
| pinned: true | |
| tags: | |
| - backyard-ai | |
| - an-adventure-in-thousand-token-wood | |
| - well-tuned | |
| - gradio | |
| short_description: Apply the color grade from one image to another image | |
| # 🌓 Color Grade Transfer | |
| **Transfer color grade directly from reference image to source image without manual color grading.** | |
| [](https://huggingface.co/build-small-hackathon) | |
| [](https://huggingface.co/build-small-hackathon) | |
| [](https://huggingface.co/build-small-hackathon) | |
| [](https://youtu.be/DqlLDDgV3kQ) | |
| [](https://x.com/ovi054/status/2064060651706925403) | |
| [](https://huggingface.co/spaces/build-small-hackathon/Color-Grade-Transfer) | |
| ## 📖 Overview | |
| It transfers the color grading from a reference image directly onto a source image. | |
| ## 🏆 Hackathon Patches | |
| | Patch | Status | | |
| | :--- | :--- | | |
| | 🔬 **Small Models Only** — `Qwen-Image-Edit-2511` at 20B parameters, well under the 32B limit | ✅ | | |
| | 🔌 **Off the Grid** — No cloud APIs, runs entirely on local GPU | ✅ | | |
| | 🎯 **Well-Tuned** — Custom LoRA [`ovi054/QIE-2511-Color-Grade-Transfer-LoRA`](https://huggingface.co/ovi054/QIE-2511-Color-Grade-Transfer-LoRA) published on Hub | ✅ | | |
| | 📓 **Field Notes** — [Blog post on what I built and learned](https://huggingface.co/blog/ovi054/color-grade-transfer) | ✅ | | |
| ### Key Features | |
| * **Direct Color Transfer:** Copies styling from a reference image to a source image without manual grading. | |
| * **4-Step Inference:** Uses a lightning adapter for fast, low-step generation. | |
| * **Aspect Ratio Alignment:** Uses an internal VAE dimension calculation 1MP to ensure the 2-D RoPE coordinate systems match, eliminating structural pixel shifts during inference. | |
| * **Interactive UI:** Features a side-by-side image comparison slider. | |
| * **MCP Compliant:** Work as a backend tool for Model Context Protocol clients. | |
| --- | |
| <!-- ### 🛠️ Core Constraints | |
| * **Small Models Only:** Powered by the `Qwen-Image-Edit-2511` architecture family running at 20B parameters safely satisfying the 32 Billion parameter limit. | |
| * 🔌 **Off the Grid (Local-First):** **No cloud APIs are used.** The pipeline loads the model weights and runs entirely on the host GPU hardware. | |
| * 🎯 **Well-Tuned:** Utilizes a custom fine-tuned LoRA adapter published directly on my Hugging Face Hub (`ovi054/QIE-2511-Color-Grade-Transfer-LoRA`). | |
| --- | |
| --> | |
| ## 🧠 LoRA Fine-Tuning Process | |
| Curating a clean dataset for custom style mapping is often the bottleneck of training. To overcome this, a systematic data-generation technique was engineered to produce high-fidelity, bidirectional training pairs. | |
| ### The Dataset Recipe | |
| 1. **Palette Extraction:** Two entirely different content images were chosen. | |
| 2. **Homogeneous Grading:** The exact same color palette was applied to both images so they shared an identical color profile. | |
| 3. **Cross-Pair Mapping:** * The newly graded version of *Image B* was assigned as the color-style reference for *Image A*. | |
| * The inputs were then flipped, mapping the graded version of *Image A* as the reference for *Image B*. | |
| 4. This instantly generated **two highly consistent training pairs** per asset set, allowing the dataset to scale efficiently without content bleeding or style loss. | |
| ### Versatility & Flexibility | |
| Because the dataset decoupling separated semantic structure from global grading parameters, the fine-tuned LoRA natively generalizes across all input configurations: | |
| * 👤 ↔️ 👤 **Character to Character** | |
| * 🏞️ ↔️ 🏞️ **Scene to Scene** | |
| * 👤 ↔️ 🏞️ **Character to Scene** / **Scene to Character** | |
| ### ⚙️ Training Hyperparameters | |
| The model was fine-tuned using the following precise configuration settings: | |
| | Configuration Category | Parameter | Value / Setting | | |
| | :--- | :--- | :--- | | |
| | **Saving Settings** | Save Precision | `bf16` | | |
| | **Learning Rate** | Learning Rate | `0.0001` | | |
| | | Optimizer | `AdamW` | | |
| | **Dataset Settings** | Base Resolution | 1024 * 1024 | | |
| | | Enable Bucket | True (`open`) | | |
| | | Min Bucket Reso | `128` | | |
| | | Max Bucket Reso | `8192` | | |
| | | Bucket Reso Steps | `64` | | |
| | **Network Settings** | Network Rank Dim (Rank) | `16` | | |
| | | Network Alpha | `16` | | |
| --- | |
| ## ⚙️ Tech Stack | |
| * **Base Model:** `Qwen/Qwen-Image-Edit-2511` | |
| * **LoRA Adapters:** | |
| * `ovi054/QIE-2511-Color-Grade-Transfer-LoRA` (Color grade transfer fine-tune) | |
| * `lightx2v/Qwen-Image-Edit-2511-Lightning` (4-step inference) | |
| * **Frontend:** Gradio | |
| --- | |
| ## 🔗 Project Links | |
| ### Live Demo | |
| * **Hugging Face Space:** [Color Grade Transfer](https://huggingface.co/spaces/build-small-hackathon/Color-Grade-Transfer) | |
| ### Blog | |
| * **Blog Post:** [Color Grade Transfer — Instant Cinematic Tone Matching](https://huggingface.co/blog/ovi054/color-grade-transfer) | |
| ### Social Media & Demo | |
| * **Twitter/X:** [https://x.com/ovi054/status/2064060651706925403](https://x.com/ovi054/status/2064060651706925403) | |
| * **Hugging Face Post:** [https://huggingface.co/posts/ovi054/229194823175599](https://huggingface.co/posts/ovi054/229194823175599) | |
| * **Youtube Video:** [https://youtu.be/DqlLDDgV3kQ](https://youtu.be/DqlLDDgV3kQ) | |
| Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference |