蚂蚁 inclusionAI 开源 6B 图像生成与编辑模型 LLaDA-Image

LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes

Introduction

LLaDA-Image is a competitive 6B-parameter open-source unified image generation and editing model family. It includes LLaDA-Image, a 50-step Base model for high-quality text-to-image generation and instruction-guided editing, and LLaDA-Image-Turbo, a 4-step distilled model for fast generation and editing. Both variants support practical text-to-image generation, VQ-conditioned generation, reference-image editing, and Chinese--English text rendering.

News

• 2026-09-04: We released the LLaDA-Image Base and Turbo checkpoints together with the inference code.

Highlights

• Unified generation and editing. A single checkpoint supports text-to-image generation and reference-preserving, instruction-guided editing without a separate editing backbone.
• Unified diffusion model. Both backone and DiT are diffusion models, trained in a unified framework.
• Realistic image generation. LLaDA-Image produces high-quality images with rich visual details, natural lighting, and coherent compositions.
• Image-only pre-training for visual-prior learning. The report establishes the visual prior through image-only pre-training and mid-training before introducing paired language supervision and joint generation--editing training.
• Efficient inference with distilled model. LLaDA-Image-Turbo uses Twin-DMD distillation to deliver fast image generation and editing in only 2--4 sampling steps.
• SOTA on Qwen-Image-Bench. LLaDA-Image achieves state-of-the-art overall scores of 53.53 in English and 53.38 in Chinese.

Model Zoo

Opensource Plan

• • Inference code and model weights
• • Training code (coming soon)

Quick Start

1. Create an environment

git clone https://github.com/inclusionAI/LLaDA-Image.git
cd LLaDA-Image

conda create -n llada-image python=3.11 -y
conda activate llada-image

pip install -r requirements.txt

2. Run inference

LLaDA-Image (Base)

import torch

from src import LLaDAImagePipeline

# Load the pipeline. The model is downloaded from Hugging Face on first use.
pipe = LLaDAImagePipeline.from_pretrained(
    "inclusionAI/LLaDA-Image",
    torch_dtype=torch.bfloat16,
    device="cuda",
)

# Generate an image.
prompt = (
    "A cinematic photograph of a red fox standing in fresh snow, "
    "soft winter light, detailed fur, shallow depth of field"
)
negative_prompt = ""

image = pipe(
    prompt=prompt,
    negative_prompt=negative_prompt,
    generation_mode="text",
    height=1024,
    width=1024,
    num_inference_steps=50,
    guidance_scale=5.0,
    generator=torch.Generator("cuda").manual_seed(42),
).images[0]

image.save("llada-image-base.png")

LLaDA-Image-Turbo

import torch

from src import LLaDAImagePipeline

# Load the distilled Turbo checkpoint.
pipe = LLaDAImagePipeline.from_pretrained(
    "inclusionAI/LLaDA-Image-Turbo",
    torch_dtype=torch.bfloat16,
    device="cuda",
)

prompt = "A quiet observatory above a sea of clouds at sunrise, golden light, wide-angle photograph"

image = pipe(
    prompt=prompt,
    generation_mode="text",
    height=1024,
    width=1024,
    num_inference_steps=4,
    guidance_scale=1.0,
    generator=torch.Generator("cuda").manual_seed(42),
).images[0]

image.save("llada-image-turbo.png")

Generation modes

image = pipe(
    prompt="A quiet observatory above a sea of clouds at sunrise",
    generation_mode="vq",
    height=1024,
    width=1024,
    num_inference_steps=50,  # Use 4 for LLaDA-Image-Turbo.
    guidance_scale=5.0,  # Use 1.0 for few-step inference.
    generator=torch.Generator("cuda").manual_seed(42),
).images[0]

from diffusers.utils import load_image

reference_image = load_image("/path/to/input.png")
image = pipe(
    prompt="Turn it into a watercolor painting",
    image=reference_image,
    generation_mode="editing",
    height=1024,
    width=1024,
    num_inference_steps=50,  # Use 4 for LLaDA-Image-Turbo.
    guidance_scale=5.0,  # Use 1.0 for few-step inference.
    generator=torch.Generator("cuda").manual_seed(43),
).images[0]

Citation

@article{LLaDAImage,
title = {LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes},
author = {Chuyan Chen and Haoxing Chen and Kun Chen and Zhenglin Cheng and Long Cui and Ruishan Fang and Zhangxuan Gu and Zhicheng Huang and Zhenzhong Lan and Yuanting Lei and Haoquan Li and Jianguo Li and Rongchuan Li and Sidu Li and Tao Lin and Deyuan Liu and Jiacheng Liu and Lin Liu and Yuxuan Lou and Zhisheng Lu and Yuxin Ma and Shuheng Shen and Peng Sun and Chaoyang Wang and Hongjun Wang and Xiaomei Wang and Yongxin Wang and Chengzhang Wu and Hongru Wu and Jun Xie},
journal = {arXiv preprint arXiv:2609.03796},
year = {2026}
}