Skip to content

armgit / kokon

Public Imported from GitHub
0

Edit photos by describing the change, on your own GPU. A free, open-source alternative to Nano Banana and ChatGPT image editing: photos stay on your computer, no daily limit. One installer for Windows, Mac and Linux sets up the best open model (Qwen-Image 2.1). MCP server for AI agents.

README: New in 0.12 (Layers lab image linked to the 0.12 video), 0.11 video as a link, features and roadmap

Gabriele Lozuponece7723b91006
diff --git a/README.md b/README.md
index 132a17d..5b165e4 100644
--- a/README.md
+++ b/README.md
@@ -40,7 +40,8 @@
<p align="center">
<a href="https://kokon.app/">Website</a> ·
<a href="#install">Install</a> ·
- <a href="#new-in-011-use-it-from-your-phone-or-run-it-as-a-server">Phone & server</a> ·
+ <a href="#new-in-012-split-any-image-into-layers">New in 0.12</a> ·
+ <a href="#since-011-use-it-from-your-phone-or-run-it-as-a-server">Phone & server</a> ·
<a href="#what-you-can-do">Features</a> ·
<a href="#examples">Examples</a> ·
<a href="#use-it-from-your-ai-agent">AI agents</a> ·
@@ -51,7 +52,7 @@
https://github.com/user-attachments/assets/8851c580-99b9-432a-82be-b6d42fa9a749
-<p align="center"><a href="https://youtu.be/y2NAJkZ4vH0">Watch in 4K on YouTube</a> · <a href="https://youtu.be/qGiGXasJJNI">What's new in 0.10 (42 s)</a></p>
+<p align="center"><a href="https://youtu.be/y2NAJkZ4vH0">Watch in 4K on YouTube</a> · <a href="https://youtu.be/WDbHxkbpU4s">What you can do with Kokon (85 s)</a> · <a href="https://youtu.be/eGr9yYe7NVc">What's new in 0.12</a></p>
<p align="center">
<a href="https://github.com/GabrieleLozupone/kokon/releases/latest"><picture>
@@ -72,16 +73,35 @@ https://github.com/user-attachments/assets/8851c580-99b9-432a-82be-b6d42fa9a749
---
-## New in 0.11: use it from your phone, or run it as a server
+## New in 0.12: split any image into layers
+
+<p align="center">
+ <a href="https://youtu.be/eGr9yYe7NVc"><img src="assets/readme/layers-0.12.webp" alt="The Layers lab: a Halloween poster split into its layers (girl, spider, ghosts, bats, text and the filled background), lifted apart in 3D, with the layer list and Export to PSD" width="860"></a>
+</p>
+<p align="center"><a href="https://youtu.be/eGr9yYe7NVc">▶ Watch the 0.12 video (2:21)</a> · <a href="https://kokon.app/image-to-layers/">Try the layers in your browser</a></p>
+
+- **Layers lab** (experimental): click the things you want on their own layer. Kokon cuts each one out and paints
+ the background behind it, so you can move, scale, hide or edit any piece, expand one that was cut off by the frame,
+ and save one image or **export a PSD** for Photoshop, GIMP or Photopea.
+- **Blend into scene** (experimental): after a move, Kokon redraws the shadows, or reflections on wet or shiny ground.
+- **Paint with colours**: one colour per thing, and say what goes there, right on the picture; **Select** picks an
+ object with one click.
+- **Prompt+ for painted areas and Expand**, with a Standard or Detailed level.
+- **Kokon's own Mac engine is the default** on Macs with 16 GB or more: about a minute for a new 1-megapixel image on
+ an M2 Pro, four times faster than before.
+- **AI marking**: every image says, in its file and in an invisible watermark, that it was made with AI
+ ([docs/ai-marking.md](docs/ai-marking.md)).
+
+---
+
+## Since 0.11: use it from your phone, or run it as a server
<p align="center">
<a href="https://kokon.app/self-hosted/"><img src="assets/readme/other-devices.webp" alt="A computer with a graphics card runs Kokon; a MacBook and an iPhone use it in the browser over the home network" width="860"></a>
</p>
Your computer with the graphics card makes the images; your phone, tablet or laptop uses Kokon in a browser.
-Nothing goes through a cloud, and there is no account.
-
-https://github.com/user-attachments/assets/ccf8da7c-175d-4d1b-9976-91eaa7bddd09
+Nothing goes through a cloud, and there is no account. [▶ Watch the 0.11 video (77 s)](https://youtu.be/XnC_7P2_cww)
- **Other devices:** open **Settings → Other devices**, set a password and scan the QR code with your phone.
Add Kokon to the home screen and it opens like an app. Off until you turn it on; 5 wrong passwords make
@@ -310,6 +330,8 @@ files are not tested by Kokon; you can switch to the official files at any time
| Several photos + a sentence | **Combine** them | Refer to them as “image 1”, “image 2”… and drag to reorder |
| A brushed area + an action | **Inpaint**: Change, Remove, Replace or Add | Remove needs no prompt |
| Dragged edges | **Expand** the photo (outpainting) | Or type pixel or percent values |
+| Clicks on the objects | **Split it into layers** (Layers lab, experimental) | The background is filled behind them; move, edit, export a PSD |
+| Areas painted in colours + what goes there | **Several changes in one go** | Only what you painted changes |
| Any result | **Upscale** to 2×, 4K, the source size or a custom width | With the upscaler model, in seconds |
| Any result | **Colour-grade** it with a LUT | Eight built-in looks (Neutral takes out a yellow cast) or your own `.cube` files, live preview with intensity |
| A short idea, in any language | **Prompt+** writes the detailed prompt first | You watch it being written; for edits it looks at your photo. Runs on the model Kokon already has: no extra download, a few seconds more |
@@ -757,8 +779,10 @@ or macOS version and the log from `KokonData/logs` (see the table above).
- [x] **0.11:** the interface in a browser on your other devices, served by Kokon itself, with a password,
and a Docker image for NVIDIA ([#15](https://github.com/GabrieleLozupone/kokon/issues/15))
- [ ] Docker image for AMD and Intel (Vulkan); the desktop app as a client of a Kokon server elsewhere
-- [x] Kokon's own engine for Apple Silicon (GPU, CPU matrix unit and Neural Engine together; experimental, 0.11.1:
- text to image about 4× faster on an M2 Pro)
+- [x] Kokon's own engine for Apple Silicon (GPU, CPU matrix unit and Neural Engine together; 0.11.1, the default on
+ Macs with 16 GB or more since 0.12: text to image about 4× faster on an M2 Pro)
+- [x] **0.12:** the Layers lab (split an image into layers, the background filled, PSD export; experimental), paint
+ with colours, AI marking (metadata and an invisible watermark)
- [ ] Intel GPUs through Vulkan (to verify)
- [ ] Background removal and transparent cutouts
- [ ] Batch edits: one instruction for a whole folder
diff --git a/assets/readme/layers-0.12.webp b/assets/readme/layers-0.12.webp
new file mode 100644
index 0000000..7f8a1a7
Binary files /dev/null and b/assets/readme/layers-0.12.webp differ