# DreamLite
**Repository Path**: thzsen/DreamLite
## Basic Information
- **Project Name**: DreamLite
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No
## Statistics
- **Stars**: 0
- **Forks**: 0
- **Created**: 2026-04-30
- **Last Updated**: 2026-04-30
## Categories & Tags
**Categories**: Uncategorized
**Tags**: None
## README
# DreamLite: A Lightweight On-Device Unified Model for Image Generation and Editing
[](https://huggingface.co/spaces/carlofkl/DreamLite)
[](https://arxiv.org/abs/2603.28713)
[](https://carlofkl.github.io/dreamlite/)
[](https://github.com/ByteVisionLab/DreamLite)
## 🌿 Overview
We introduce **DreamLite**, a compact and unified on-device diffusion model (**0.39B**) that seamlessly supports both **text-to-image generation** and **text-guided image editing** within a single network architecture.
Built upon a pruned mobile U-Net backbone, DreamLite unifies multimodal conditioning through **In-Context Spatial Concatenation** directly in the latent space. By leveraging progressive step distillation, DreamLite achieves ultra-fast **4-step inference**, capable of generating or editing a **1024×1024** image in ~**3 seconds** on an iPhone 17 Pro (powered by 4-bit Qwen-VL and fp16 VAE+UNet) — operating **fully on-device with zero cloud dependency**.
Figure 1. The overall unified architecture of DreamLite.
---
## 📰 News
- **[2026.04]** 🎉🎉🎉 We officially released the inference code.
- **[2026.03]** 🎉🎉🎉 DreamLite is publicly announced! Check out our [project page](https://carlofkl.github.io/dreamlite/) and [arXiv paper](https://arxiv.org/abs/2603.28713).
---
## 🎬 On-Device Demo
Experience real-time generation and editing on an iPhone 17 Pro. No internet connection or cloud processing required.
| Human Portrait & Style Transfer |
Nature Landscape & Background Swap |
Product & Object Replacement |
|
|
|
> **Note**: If demos fail to render natively on GitHub, please visit our [Project Page](https://carlofkl.github.io/dreamlite/) to watch the full demonstrations.
---
## ⚙️ Getting Started
### 1. Environment Setup
```bash
# Clone the repository
git clone https://github.com/ByteVisionLab/DreamLite.git
cd DreamLite
# Create and activate a conda environment
conda create -n dreamlite python=3.10 -y
conda activate dreamlite
# Install dependencies
pip install -r requirements.txt
```
Ensure the model weights (DreamLite-base and DreamLite-mobile) are placed in the following directory structure:
```
DreamLite/
├── models/
│ ├── DreamLite-base/
│ └── DreamLite-mobile/
```
### 2. Inference via CLI
You can readily generate or edit images utilizing our provided command-line interfaces.
```bash
# ==========================================
# DreamLite-base: 28 Steps (High Fidelity)
# ==========================================
# Text-to-Image Generation
python infer.py --prompt "A close-up of a fire spitting dragon cinematic shot."
# Text-guided Image Editing
python infer.py --prompt "Transfer this image to oil-painting style." --image_path ./inputs/source.png
# ==========================================
# DreamLite-mobile: 4 Steps (Ultra Fast)
# ==========================================
# Text-to-Image Generation
python infer_mobile.py --prompt "A portrait of a young woman with flowers."
# Text-guided Image Editing
python infer_mobile.py --prompt "Change the background to a dense forest." --image_path ./inputs/source.png
```
### 3. Benchmark Evaluation
We provide comprehensive benchmark evaluation scripts (GenEval & ImgEdit) to facilitate performance comparisons between DreamLite and other state-of-the-art models. Please configure your local dataset paths within `tools/benchmark/infer_geneval.py` and `tools/benchmark/infer_imgedit.py` prior to execution.
```bash
# Run the benchmark evaluation
python tools/benchmark/infer_geneval.py --save_dir ./output/benchmark/geneval_output --geneval_json "YOUR_GENEVAL/evaluation_metadata.jsonl"
python tools/benchmark/infer_imgedit.py --save_dir ./output/benchmark/imgedit_output --json_path "YOUR_IMGEDIT_PATH/ImgEdit/Benchmark/Basic/basic_edit.json" --img_root "YOUR_IMGEDIT_IMAGES_PATH/ImgEdit/Benchmark/singleturn"
```
### 4. Interactive Gradio Demo
We provide a user-friendly web interface powered by Gradio. You can try our live demo on Hugging Face Spaces, or deploy it locally on your own machine (GPU/CPU).
[](https://huggingface.co/spaces/carlofkl/DreamLite)
To run the interactive demo locally:
```bash
# Launch the local web server
python tools/app.py
```
## 🤗 Checkpoints
We offer two distinct variants of the DreamLite model to provide an optimal balance between visual fidelity and on-device inference latency.
> [!NOTE]
> **Model Access:** Model weights are currently undergoing safety review. To request early access, please contact us at 📧 klfeng1206@outlook.com with an email titled **"DreamLite Access Request"**.
>
> In your email, please ensure to include:
> 1. **Your Name & Affiliation** (e.g., University, Company, or personal portfolio).
> 2. **Intended Use Case** (Please briefly describe how you plan to use the DreamLite model).
⚠️ **Important Usage and Compliance Notice**:
By accessing and using these models, you agree to abide by our ethical guidelines. These models must **NOT** be used to generate, edit, or distribute any content that is sexually explicit, pornographic, violent, discriminatory, or otherwise illegal. We strictly prohibit the use of DreamLite for malicious purposes.
| Model Variant |
Params |
Resolution |
Steps |
Guidance |
| DreamLite (Base) |
0.39B |
1024×1024 |
28 |
CFG & IMG_CFG |
| DreamLite (Mobile) |
0.39B |
1024×1024 |
4 |
No CFG |
## 📊 Main Results
Quantitative comparison with state-of-the-art methods on generation and editing benchmarks.
Text-to-Image generation comparison.
Text-guided image editing comparison.
| Method |
Params |
GenEval ↑ |
DPG ↑ |
ImgEdit ↑ |
GEdit-EN-Q ↑ |
| FLUX.1-Dev / Kontext |
12B |
0.67 |
84.0 |
3.76 |
6.79 |
| BAGEL |
7B |
0.82 |
85.1 |
3.42 |
7.20 |
| OmniGen2 |
4B |
0.80 |
83.6 |
3.44 |
6.79 |
| LongCat-Image / Edit |
6B |
0.87 |
86.6 |
4.49 |
7.55 |
| DeepGen1.0 |
2B |
0.83 |
84.6 |
4.03 |
7.54 |
| SANA-1.6B |
1.6B |
0.67 |
84.8 |
- |
- |
| SANA-0.6B |
0.6B |
0.64 |
83.6 |
- |
- |
| SnapGen++ (small) |
0.4B |
0.66 |
85.2 |
- |
- |
| VIBE |
1.6B |
- |
- |
3.85 |
7.28 |
| EditMGT |
0.96B |
- |
- |
2.89 |
6.33 |
| DreamLite (Ours) |
0.39B |
0.72 |
85.8 |
4.11 |
6.88 |
## 🎛️ LoRA Fine-tuning
We provide comprehensive support for LoRA fine-tuning and inference, enabling lightweight customization of DreamLite on your own domain-specific datasets.
For detailed instructions, training scripts, and examples, please refer to our dedicated **[LoRA Fine-Tuning Guide](lora/README.md)**.
## 📑 Open-Source Plan
- [X] Release paper on arXiv
- [X] Release inference code
- [X] Release LoRA training
- [ ] Release model weights on HuggingFace
- [X] Release online demo
- [ ] On-device Deployment Reference
## 🙏 Acknowledgement
We thank the great work from [SDXL](https://github.com/Stability-AI/generative-models), [SnapGen](https://snap-research.github.io/snapgen/), [Qwen](https://qwen.ai/home) and [TAESDXL](https://github.com/madebyollin/taesd). The work is under supervision from Prof. Wangmeng Zuo.
## 🪪 License
**Code**: Apache-2.0
**Model weights**: see WEIGHTS_LICENSE, CC BY-NC 4.0
## 📄 Citation
If our work assists your research, feel free to give us a star ⭐ or cite us using:
```bibtex
@article{feng2026dreamlite,
title={DreamLite: A Lightweight On-Device Unified Model for Image Generation and Editing},
author={Kailai Feng and Yuxiang Wei and Bo Chen and Yang Pan and Hu Ye and Songwei Liu and Chenqian Yan and Yuan Gao},
journal={arXiv preprint arXiv:2603.28713},
year={2026}
}
``` 