Flux-LoRA-DLC

Flux-LoRA-DLC is an experimental, advanced image generation and image-to-image styling platform built on top of the state-of-the-art black-forest-labs/FLUX.1-dev text-to-image foundation model. The suite includes an integrated multi-LoRA routing manager packed with a gallery collection of over 250 highly distinct aesthetic DLC adapters (such as Koda film style, Ghibli cartoon art, and Sketch Smudge texture). For real-time execution feedback, the pipeline couples a lightweight madebyollin/taef1 preview autoencoder to stream step-by-step denoising passes directly to the front-end before invoking a specialized high-fidelity VAE for final output rendering. Featuring an open-ended custom repository lookup field for live third-party Hugging Face LoRA mounting, Flux-LoRA-DLC provides an ultra-flexible playground for creators mapping advanced latent transformations.

https://github.com/user-attachments/assets/09318576-006d-4ccd-8efc-0360c7b289e3

Key Features

• Massive 250+ LoRA Library: Instantly browse and hot-swap through an extensive pre-configured array of artistic, cinematic, cartoon, and highly realistic LoRA adapters via a single interactive grid.
• On-the-Fly External Mounting: Dynamically download and load any public FLUX-compatible adapter weights directly during active sessions by pasting its Hugging Face repository slug.
• Latent Denoising Previews: Overrides standard generation pipelines with a custom rendering loop that hooks directly into the discrete flow-matching Euler scheduler to stream step-by-step image passes.
• Image-to-Image Conditioning: Supports structural image-to-image transformations accompanied by a granular denoise strength factor to precisely balance source image influence with prompt weight.
• Sleek Steel Blue Theme: Wrapped in an intuitive, responsive dashboard styled with deep gray and steel blue colors, incorporating real-time mathematical progress containers.

Repository Structure

├── app.py
├── LICENSE
├── pre-requirements.txt
├── pyproject.toml
├── README.md
├── requirements.txt
└── uv.lock

Installation and Requirements

To run Flux-LoRA-DLC locally, set up a Python environment with the dependencies listed below. A dedicated CUDA-capable GPU with sufficient VRAM is required to compile and serve FLUX.1 weights.

Standard PIP Installation

1. Upgrade your package manager to fulfill current alignment states:

pip install pip>=26.1

2. Install standard core configurations:

pip install -r requirements.txt

Running with uv (Recommended)

uv is an extremely fast Python package and project manager written in Rust, which ensures rapid environment synchronization and complete reproducibility.

**Step 1 — Install uv**

• macOS / Linux: curl -LsSf https://astral.sh/uv/install.sh | sh
• Windows: powershell -c "irm https://astral.sh/uv/install.ps1 | iex"

Step 2 — Clone the repository

git clone https://github.com/PRITHIVSAKTHIUR/Flux-LoRA-DLC.git
cd Flux-LoRA-DLC

Step 3 — Initialize the project and install dependencies

uv sync

Step 4 — Run the script

uv run app.py

Core Requirements List

The application relies on the following primary packages (defined in requirements.txt):

git+https://github.com/huggingface/accelerate.git
git+https://github.com/huggingface/diffusers.git
huggingface_hub
sentencepiece 
transformers==4.57.6
torchvision
gradio==6.14.0
spaces
torch==2.11.0
numpy
peft

Usage

Once the FastAPI web client loads into your browser environment (typically mapped to http://127.0.0.1:7860/):

1. Select an Adapter: Click on any stylistic preset card inside the 250+ LoRA DLC's gallery layout, or provide an external model shortcut inside the Enter Custom LoRA panel.
2. Type Your Instruction: Enter your descriptive text inside the primary input area. The model seamlessly merges your text with the corresponding model's trigger tokens.
3. Advanced Settings (Optional): Open the Advanced Options accordion to swap out image canvas dimensions (from 256px up to 1536px), step sizes, CFG scales, or append reference images for Image-to-Image styling.
4. Generate: Press the Generate button or tap enter to start streaming live progressive image transformations straight onto the viewport.

License and Source

• License: Apache License 2.0
• GitHub Repository: https://github.com/PRITHIVSAKTHIUR/Flux-LoRA-DLC