---
license: apache-2.0
library_name: diffusers
pipeline_tag: image-to-image
tags:
  - image-editing
  - multi-image
  - diffusers
  - joyai
base_model:
  - Qwen/Qwen3-VL-8B-Instruct
---
# JD Open Source - Open Technology, Shared Future.
[中文](./README_CN.md)

## Our Mission
We are dedicated to empowering developers and enterprises through open technology, collectively building an efficient,
reliable, and innovative tech ecosystem. We believe that open source is a bridge connecting technology with the
community, accelerating technological accessibility and value creation.

## Our Governance
Our open-source projects operate under a transparent governance model, ensuring their healthy and sustainable growth.
We are guided by:
- Open Decision-Making: All major technical decisions are openly discussed within the community.
  We welcome feedback and suggestions from everyone.
- Meritocracy: Roles and permissions are based on an individual's contributions to the project.
  Anyone who consistently contributes has the opportunity to become a core maintainer.
- Code of Conduct: We strictly adhere to our Code of Conduct to ensure a friendly, inclusive,
  and respectful community for all.

## How to Get Involved
We welcome everyone with a passion for technology to join our community, whether you are a seasoned developer or
just starting out. Here are a few ways you can contribute:
- Submit an Issue: Found a bug or have a new feature idea? Feel free to open an issue in our project repositories.
- Contribute Code: Submit your code fixes or new features via a Pull Request. Please read the project's contribution
  guide first.
- Improve Documentation: Help us translate or improve our documentation to benefit more users.
- Join the Discussion: Participate in our community forums or chat groups to share your thoughts and experiences.

## Our Projects
You can find all our open-source projects here https://github.com/jd-opensource, or visit our homepage for more information.

## Contact Us
org.ospo1@jd.com
# JoyAI-Image Edit Plus

JoyAI-Image Edit Plus is a multi-image instruction-guided editing model from the [JoyAI-Image](https://github.com/jd-opensource/JoyAI-Image) family. It accepts **multiple reference images** and a text instruction to generate a new image that combines elements from the references according to the instruction.

## Model Architecture

| Component | Model | Size |
|-----------|-------|------|
| Text Encoder | Qwen3-VL-8B-Instruct | 8B |
| Transformer (MMDiT) | JoyImageEditPlusTransformer3DModel | 16B |
| VAE | AutoencoderKLWan | 240M |
| Scheduler | FlowMatchEulerDiscreteScheduler | - |

## Installation

`JoyImageEditPlusPipeline` has not yet been merged into the official diffusers release. Before it is available in a stable version, you need to install diffusers from the PR branch:

```bash
pip install git+https://github.com/tangyanf/diffusers.git@add-joyimage-edit-plus
```

If you have already installed diffusers, make sure to uninstall it first:

```bash
pip uninstall diffusers -y
pip install git+https://github.com/tangyanf/diffusers.git@add-joyimage-edit-plus
```

Once the PR is merged into the official diffusers repository, you can switch back to the standard installation:

```bash
pip install diffusers --upgrade
```

## Usage

```python
import torch
from PIL import Image
from diffusers import JoyImageEditPlusPipeline

pipe = JoyImageEditPlusPipeline.from_pretrained(
    "jdopensource/JoyAI-Image-Edit-Plus-Diffusers",
    torch_dtype=torch.bfloat16,
).to("cuda")

# Load reference images
images = [
    Image.open("reference_0.png").convert("RGB"),
    Image.open("reference_1.png").convert("RGB"),
]

# Determine output resolution from the last reference image
target_h, target_w = pipe.vae_image_processor.get_default_height_width(images[-1])

# Generate
result = pipe(
    images=images,
    prompt="Combine the person from the second image with the scene from the first image.",
    negative_prompt="low quality, blurry, deformed",
    height=target_h,
    width=target_w,
    num_inference_steps=30,
    guidance_scale=4.0,
    generator=torch.Generator(device="cuda").manual_seed(42),
)
result.images[0].save("output.png")
```

## Example

**Prompt:** "The woman is lovingly holding the cute puppy in her arms"

| Input 0 | Input 1 | Output |
|---------|---------|--------|
| ![input_0](examples/input_0.png) | ![input_1](examples/input_1.png) | ![output](examples/output.png) |

## Recommended Parameters

| Parameter | Value |
|-----------|-------|
| `num_inference_steps` | 30 |
| `guidance_scale` | 4.0 |
| `torch_dtype` | `torch.bfloat16` |
| Resolution | Auto-detected via `vae_image_processor.get_default_height_width()` (1024-base buckets) |

## CLI Inference

```bash
python inference.py \
    --model_path jdopensource/JoyAI-Image-Edit-Plus-Diffusers \
    --images examples/input_0.png examples/input_1.png \
    --prompt "The woman is lovingly holding the cute puppy in her arms" \
    --num_inference_steps 30 \
    --guidance_scale 4.0 \
    --seed 42 \
    --output output.png
```

## Model Details

- **Developed by**: Sky Meilin
- **License**: Apache-2.0
- **Diffusers version**: >= 0.39.0
- **Framework**: PyTorch

## Citation

```bibtex
@misc{joyai-image-2025,
  title={JoyAI-Image: A Unified Multimodal Foundation Model for Image Understanding, Generation, and Editing},
  author={Joy Future Academy, JD},
  year={2025},
  url={https://github.com/jd-opensource/JoyAI-Image}
}
```