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.

docs: STATUS.md with what is in progress, next and known issues

Gabriele Lozuponed2d2ce5ab514
diff --git a/README.md b/README.md
index 820ffe1..a14f85e 100644
--- a/README.md
+++ b/README.md
@@ -705,14 +705,15 @@ or macOS version and the log from `KokonData/logs` (see the table above).
- [x] Qwen's official 8-step Turbo model for every preset
- [x] Prompt+: the prompt enhancer on the model Kokon already has (0.10.0)
- [x] Your own LoRA files, per project (0.10.0, beta)
-- [ ] AMD and Intel GPUs through Vulkan (beta now; works on NVIDIA, to verify on AMD/Intel)
+- [x] AMD GPUs through Vulkan (beta; RX 7900 XTX and RX 9060 XT reported working, RX 6000 cards still slow)
+- [ ] **0.11:** the interface in the browser, served by Kokon itself, on your local network with a password;
+ then a Docker image for NVIDIA ([#15](https://github.com/GabrieleLozupone/kokon/issues/15))
+- [ ] Intel GPUs through Vulkan (to verify)
- [ ] Background removal and transparent cutouts
- [ ] Batch edits: one instruction for a whole folder
-- [ ] Curated LoRAs tested with Kokon, installed in one click
-- [ ] Headless server with the interface in the browser, then Docker
- ([#15](https://github.com/GabrieleLozupone/kokon/issues/15))
- [ ] Plugins for Krita, GIMP and Photoshop through the local API
+What is in progress right now, known issues and where help is welcome: [docs/STATUS.md](docs/STATUS.md).
Have an idea? [Start a discussion](https://github.com/GabrieleLozupone/kokon/discussions) or 👍 an existing one.
## Build from source
diff --git a/docs/STATUS.md b/docs/STATUS.md
new file mode 100644
index 0000000..1862e3f
--- /dev/null
+++ b/docs/STATUS.md
@@ -0,0 +1,64 @@
+# Status
+
+**Updated 2026-10-22.** 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: [0.10.1](https://github.com/GabrieleLozupone/kokon/releases/tag/v0.10.1) (2026-10-22)
+
+Windows, macOS (Apple Silicon, 15+) and Linux (`.deb`, `.rpm`). Installed copies update from the app.
+
+## In progress: 0.11, Kokon as a server
+
+Tracked in [#15](https://github.com/GabrieleLozupone/kokon/issues/15); design in [linux.md](linux.md).
+- The browser UI, served by `kokon-service` itself.
+- Access from the local network: off by default, behind a password with a limit on attempts. For access from
+ outside, a guide to Tailscale or another VPN, never direct exposure.
+- A Docker image for NVIDIA (CUDA) first; an AMD/Intel (Vulkan) image once it can be tested.
+- Later: the desktop app as a client of a Kokon server elsewhere.
+
+## Next
+
+- **0.12: reliability foundations** (details soon).
+- On the list, no dates yet: a custom upscaler picker
+ ([#34](https://github.com/GabrieleLozupone/kokon/issues/34)), everything in one folder / a portable build
+ ([#26](https://github.com/GabrieleLozupone/kokon/issues/26)), translations (only with contributor help).
+
+## Known issues
+
+- **AMD RX 6000 (RDNA2) cards are slow on Vulkan** (an RX 6700 XT took ~21 s per step). Under investigation;
+ flash attention on cards without matrix cores is the main suspect. RX 7900 XTX and RX 9060 XT work well.
+- **LoRA is beta** and tested on Windows only; reports from macOS and Linux are welcome
+ ([#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). Engine speed-ups are
+ being measured.
+- 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.
+
+## Under review
+
+- [#29](https://github.com/GabrieleLozupone/kokon/pull/29) EasyCache step cache (giveen): to be A/B-tested on the
+ test set (text-to-image, edit, multi-image, LoRA) before it becomes a default.
+- [#36](https://github.com/GabrieleLozupone/kokon/pull/36) `kokon-mcp --help` (closes #5) and
+ [#37](https://github.com/GabrieleLozupone/kokon/pull/37) full HTTP API table (closes #9), both shrinivas-sn.
+
+## Help wanted
+
+- Good first issues: [#2](https://github.com/GabrieleLozupone/kokon/issues/2) gallery keyboard,
+ [#3](https://github.com/GabrieleLozupone/kokon/issues/3) site slider keyboard,
+ [#4](https://github.com/GabrieleLozupone/kokon/issues/4) reduced-motion video.
+- Hardware reports: AMD and Intel on Windows and Linux, Linux on NVIDIA outside WSL, Macs other than an M2 Pro.
+- Model proposals that meet the switch rule: [Discussion #35](https://github.com/GabrieleLozupone/kokon/discussions/35).
+
+## Recently shipped
+
+- **0.10.1** (2026-10-22): own model files never take a text-only Qwen3 as the text encoder; Linux NVIDIA blank
+ window fixed; the progress card fits small windows ([#32](https://github.com/GabrieleLozupone/kokon/issues/32));
+ open the images folder from Settings and the gallery ([#34](https://github.com/GabrieleLozupone/kokon/issues/34));
+ `kokon-service --version` ([#31](https://github.com/GabrieleLozupone/kokon/pull/31)); CI on pull requests
+ ([#25](https://github.com/GabrieleLozupone/kokon/pull/25)).
+- **0.10.0** (2026-10-20): Prompt+ (the text encoder writes the prompt, no second model), your own LoRA files
+ (beta), Kokon's own engine on every platform, a new look.
+- **0.9.4** (2026-10-16): Linux, macOS 15, colour LUTs. **0.9.3** (2026-10-15): your own model files, GPU picker,
+ texture-fix VAE, 8 GB beta.
+
+Full notes: [releases](https://github.com/GabrieleLozupone/kokon/releases) and [marketing/](../marketing/).