dMLX
Make and edit images just by asking, fully on your Mac. dMLX is free and open source: no account, no
cloud, no subscription and no per-image fees. It is a native macOS app and a local engine.
The engine uses MLX and mflux.
A small agent on your Mac plans each message.
You can use your Mac while dMLX works.
Status: v0.1 beta 5. dMLX makes only images (it generates and edits them). Video is planned.
The app is not notarized yet.
Refer to the release notes and the known issues.
Highlights
- Make and edit images just by asking. Describe an image. Then write in simple words what to change
("make the boat red"). Each image has a number. Thus you can write "image 1" or "the first one".
- No prompts to write. A vision-language model on your Mac reads the chat and examines the images.
Then it decides: a new image or an edit, the image to change, the images to use as references, and the
image model. It writes the prompt for you. It never overrides a model that you select.
- It asks when it is not sure. If a message is not clear, the agent asks one short question. If you
send a greeting or a question about the app, the agent replies and does not make an image.
- It does not start a job that would freeze your Mac. The engine does a check of the memory before
each image job. If memory is low, the engine loads models in parts. The engine stops a job before macOS
starts to swap. dMLX is for Macs with 16 GB of memory or more.
- When words are not enough, circle it. In Crop / Draw, crop the image and paint a mark on the part to
change. Then write what to do. The original image does not change.
- Drag text and objects into place. The rest stays. With MOSS Image, Ideogram 4 or FIBO 2, the agent
plans a layout: a box for each title, line of text and main object. Move a box, then redraw. The part
that you moved goes to its new place, and the rest stays where it was. Thus you can move one part and not
start again.
- Every version is kept. The app does not overwrite an image. Variations show as v1, v2, v3. You can
edit each version. You can also edit your prompt and run it again.
- Private and offline by default. After you download the models, all work occurs on your Mac. You do
not need an account or a cloud service. If you select your own AI service for the agent, your messages
and the images in the chat go to that service. The images are still made on your Mac.
- An image API on your Mac. The engine has an OpenAI-compatible images API for other apps and agents,
with no per-image fees.
What you can make
Each example is a chat in the app, with Auto set. The agent selected the model. For a removal, the
first message makes an image and the second message removes something from it.
Remove text
"remove all the text from the window" · Qwen Image 2.1 · about 5 min
Remove an object
"remove the coffee mug" · FLUX.2 Klein 4B · 36 s
Remove a person
"remove the person" · FLUX.2 Klein 4B · 40 s
Make a poster
A Portrait image with a title · Qwen Image 2.1 · about 4 min
Make a banner
A Landscape image with words · Qwen Image 2.1 · about 4 min
For exact words in an image, the agent usually selects Qwen Image 2.1. This model is slow, it needs about
9.5 GB of free memory, and its license does not permit commercial use. FLUX.2 Klein 4B is fast, but it
does not always spell words correctly.
Edit with Crop / Draw
You can write in simple words how to change a result. You can also show your request on the image first.
Open Crop / Draw below a result. Crop the image. Paint marks on it. Erase the marks that are not correct.
Click Attach edited image. Then write what to do. The app does not change the original image.
| 1 · Crop | 2 · Paint a mark | 3 · Erase an incorrect mark |
|---|
| | |
| The dimmed area is not in the prepared image. | The circle shows the area to change. The line on the table is an error. The color and brush size are below the image. | Erase removes only paint. The image below the paint does not change. |
4 · Attach and ask. Attach edited image puts the prepared image in the message box. The agent
gets the prepared image, a note that tells it the image is image 1 after Crop / Draw, and your words.
The marks are part of the prepared image. Write "remove the marks" in your message, or the result can
keep them. The prepared image is one of the 3 images that you can attach.
| Before (image 1 after Crop / Draw) | After (image 2, "Edited from image 1 after Crop / Draw") |
|---|
| |
The result has the size and the framing of the cropped area, not of the full image 1.
This is the beginning of the README. Read the rest at the original. Read the full README ↗
