*: ^† denotes using an LLM rewriter. For MJHQ(-30K), we report FID.

*: Q3/7B indicates using Qwen2.5-VL-3/7B as the external designer during inference. By default, GPT-4o is employed as the external designer to ensure the best performance. All models are evaluated using GPT-4.1.

^†: The default setting.

*：Green and Blue denote the edits of Janus-4o and Step1X-Edit respectively; Red denotes the edits of our models trained on different data corpora.

The demo T2I instructions are provided in cache/demo/tos_dataset_demo.jsonl, where each line is an instruction in json format like:

{"id": "0000", "image_path": "./cache/demo/edit_demo_0000.png", "prompt": "A yummy cupcake floating in the air dark background"}

The image_path is just a placeholder, and you can modify prompt to create your own image.

To generate images from the jsonl file, run the following script:

bash scripts/demo_t2i.sh

For each instruction, the generated image will be saved at cache/inference/demo/DIM-4.6B-T2I/{id}_gen.jpg.

The demo edit instructions are provided in cache/demo/tos_dataset_edit_demo.jsonl, where each line is an instruction in json format like:

{"id": "0", "image_path": "./cache/demo/edit_demo_0000.png", "prompt": "Remove the lemons on the table.", "image_path_target": "./cache/demo/edit_demo_0000.png"}

The image_path corresponds to the source image, and the prompt is the edit instruction. The image_path_target is just a placeholder.

In infer/demo_edit.py, use the set_designer_gpt API with your own key to set GPT-4o as the external designer for optimal performance.

# GPT-4o as external designer
model.set_designer_gpt(api_key='')

You can also use the set_designer_X API to set various open-source VLMs as the external designer. The VLMs will be automatically downloaded to local disk.

# Qwen2.5-VL as external designer
model.set_designer_qwen(version='Qwen/Qwen2.5-VL-3B-Instruct')
model.set_designer_qwen(version='Qwen/Qwen2.5-VL-7B-Instruct')

# InternVL3.5 as external designer (recommend using transformers==4.53.0)
model.set_designer_internvl(version='OpenGVLab/InternVL3_5-8B-HF')

# MiMo-VL as external designer
model.set_designer_mimo(version='XiaomiMimo/MiMo-VL-7B-RL-2508')

# GLM-4.1V as external designer (recommend using transformers==4.53.1)
model.set_designer_glm(version='THUDM/GLM-4.1V-9B-Thinking')

To generate edited images from the jsonl file, run the following script:

bash scripts/demo_edit.sh

The model will first generate a CoT-guided edit instruction for each prompt and save it to cache/inference/demo/DIM-4.6B-Edit/tos_dataset_edit_cot_demo_gen.jsonl. Then the generated images will be saved at cache/inference/demo/DIM-4.6B-Edit/{id}_edited.jpg.

We also provide a sample GPT-4o generated CoT jsonl file at cache/demo/tos_dataset_edit_cot_demo.jsonl for reference.

We provide two evaluation jsonl files according to prompt types in cache/GenEval:

1. tos_dataset.jsonl: Origin prompts.
2. tos_dataset_rewritten.jsonl: LLM-rewritten prompts.

The image_path field in each line of the jsonl is just a placeholder, please replace it with a pseudo image on your local disk first.

Run the following script to generate images:

bash scripts/eval_geneval.sh

The generated images will be saved to cache/inference/DIM-4.6B-T2I/GenEval(_rewritten). Please follow the guide in GenEval official repo for metrics calculation.

First download MJHQ-30K from the HF repo. You only need to download mjhq30k_imgs.zip. Then extract all images in the cache folder and organize them as follows:

cache
└── MJHQ-30K
    ├── animals
    │   ├── {id}.jpg
    │   ├── {id}.jpg
    │   └── ...
    ├── art
    ├── fashion
    ├── food
    ├── indoor
    ├── landscape
    ├── logo
    ├── people
    ├── plants
    └── vehicles

We have provided all prompts of MJHQ-30K in cache/MJHQ-30K/tos_dataset.jsonl. Run the following script to generate images:

bash scripts/eval_mjhq30k.sh

The generated images will be saved to cache/inference/DIM-4.6B-T2I/MJHQ-30K. We use pytorch-fid to calculate the FID on MJHQ-30K.

First download ImgEdit from the HF repo. Put the dataset in the cache folder, and organize it as follows:

cache
└── ImgEdit
    └── Benchmark
        ├── hard
        ├── multiturn
        └── singleturn
            ├── animal
            │   ├── {id}.jpg
            │   └── ...
            ├── architecture
            ├── clothes
            ├── compose
            ├── daily object
            ├── for_add
            ├── human
            ├── style
            ├── transport
            ├── judge_prompt.json
            └── singleturn.json

We provide four evaluation jsonl files according to prompt types in cache/ImgEdit:

1. tos_dataset_edit.jsonl: Origin prompts.
2. tos_dataset_edit_cot.jsonl: CoT-style prompts generated by GPT-4o.
3. tos_dataset_edit_cot_Qwen2.5-VL-3B-Instruct.jsonl: CoT-style prompts generated by Qwen2.5-VL-3B.
4. tos_dataset_edit_cot_Qwen2.5-VL-7B-Instruct.jsonl: CoT-style prompts generated by Qwen2.5-VL-7B.

Run the following script to generate images:

bash scripts/eval_imgedit.sh

The generated images will be saved to cache/inference/DIM-4.6B-Edit/ImgEdit. Please follow the guide in ImgEdit official repo for metrics calculation.

First download GEdit-Bench from the HF repo. Extract all raw images from the dataset and put them in the cache folder. Organize them as follows:

cache
└── GEdit-Bench
    └── input_image_raw
        ├── {id}.png
        ├── {id}.png
        ├── {id}.png
        ├── {id}.png
        └── ...

We provide four evaluation jsonl files according to prompt types in cache/GEdit-Bench:

1. tos_dataset_edit_en.jsonl: Origin prompts.
2. tos_dataset_edit_en_cot.jsonl: CoT-style prompts generated by GPT-4o.
3. tos_dataset_edit_en_ot_Qwen2.5-VL-3B-Instruct.jsonl: CoT-style prompts generated by Qwen2.5-VL-3B.
4. tos_dataset_edit_en_cot_Qwen2.5-VL-7B-Instruct.jsonl: CoT-style prompts generated by Qwen2.5-VL-7B.

Run the following script to generate images:

bash scripts/eval_gedit_bench.sh

The generated images will be saved to cache/inference/DIM-4.6B-Edit/GEdit-Bench. Please follow the guide in GEdit-Bench official repo for metrics calculation.