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.

STATUS: Mac engine does brushed edits and extending, 1 MP edit ~106 s

Gabriele Lozupone59b41bb3d794
diff --git a/docs/STATUS.md b/docs/STATUS.md
index 816958a..388e17c 100644
--- a/docs/STATUS.md
+++ b/docs/STATUS.md
@@ -1,6 +1,6 @@
# Status
-**Updated 2026-10-25.** What is in progress, what comes next, and where help is welcome. Kept current at the end
+**Updated 2026-10-26.** What is in progress, what comes next, and where help is welcome. Kept current at the end
of every task (see [AGENTS.md](../AGENTS.md#keeping-docsstatusmd-current)); GitHub is the source of truth.
## Current version: [0.11.0](https://github.com/GabrieleLozupone/kokon/releases/tag/v0.11.0) (2026-10-24)
@@ -25,10 +25,10 @@ Windows, macOS (Apple Silicon, 15+) and Linux (`.deb`, `.rpm`). Installed copies
([#33](https://github.com/GabrieleLozupone/kokon/issues/33) has a product-shot test).
- **Macs are slow** compared with NVIDIA cards (about 4 minutes for 1 MP on an M2 Pro 16 GB). Kokon's own Mac
engine is in development on the `macos-optimization` branch (`engine-mac/`, not released): text to image,
- Prompt+ (a prompt written in about 7–9 s) and edits with reference images (Prompt+ looking at them too), about 64–67 s
- for 1 MP text to image and ~150 s for a 1 MP edit on the same Mac (peak memory 5 GB), as an experimental switch in
- Settings → Performance (off by default). Brushed edits, extending an image, LoRAs and the upscaler still need the
- standard engine.
+ Prompt+ (a prompt written in about 7–9 s), edits with reference images (Prompt+ looking at them too), brushed edits and
+ extending an image, about 64–67 s for 1 MP text to image and ~106 s for a 1 MP edit on the same Mac (peak memory 5 GB),
+ as an experimental switch in Settings → Performance (off by default). LoRAs and the upscaler still need the standard
+ engine (not planned for its first release).
- The Windows installer is not code-signed: SmartScreen or Smart App Control may block it (README FAQ: Unblock).
- HEIC photos can't be opened on Linux yet.