Card: ComfyUI 0.4.0 and the WebGPU demo now support this release

README.md

@@ -48,7 +48,7 @@ Built by [LogoLabs](https://logolabs.org), which makes AI logo generation.
 | **GenEval** (official) | **0.577** (001: 0.550). SDXL 0.55, SD 2.1 0.50, PixArt-α 0.48, SD 1.5 0.43 (published) |
 | **Qwen-Image-Bench** (1,000 prompts) | **28.9** (001: 28.2; SD 1.5: 29.1) |
 | **Speed** | Same network as 001: 1.9 s per image on an RTX 4060 (50 steps, CUDA graphs), timed on 001 |
-| **ComfyUI / browser** | Not yet updated for 002 (see below) |
+| **ComfyUI / browser** | [ComfyUI nodes](https://github.com/logolabs/agate-comfyui) 0.4.0 and the [WebGPU demo](https://huggingface.co/spaces/Logolabs/agate-webgpu) (select Preview 002) |
 | **Licence** | MIT, for code and weights |
 | **Status** | Research preview |
 
@@ -92,11 +92,11 @@ The arguments are 001's: `seed`, `steps` (50), `cfg` (3.0), `negative_prompt` ("
 `requirements.txt`). `autoguide` steers away from the same guide model 001 ships (T40r
 step 27,600, in `guide/`); we have not re-tuned its strength for 002.
 
-**ComfyUI and the WebGPU demo are not yet updated for 002.** The
-[ComfyUI nodes](https://github.com/logolabs/agate-comfyui) download 001's single-file checkpoint, and the
-[WebGPU Space](https://huggingface.co/spaces/Logolabs/agate-webgpu) runs 001's ONNX export. Because 002 is the same
-network, the same converters should apply unchanged, but no 002 single-file checkpoint or ONNX export is published or
-tested yet.
+**ComfyUI and the WebGPU demo support 002.** The [ComfyUI nodes](https://github.com/logolabs/agate-comfyui) (0.4.0) load the single-file checkpoint in
+[`comfyui/`](https://huggingface.co/Logolabs/agate-preview-002/tree/main/comfyui), and the [WebGPU Space](https://huggingface.co/spaces/Logolabs/agate-webgpu) runs
+an fp16 ONNX export (in [`webgpu/`](https://huggingface.co/Logolabs/agate-preview-002/tree/main/webgpu)); both mark
+their outputs like the Python package. The browser build differs from the Python package by 0.1-0.2/255 on average
+(fp16 weights).
 
 ## Results
 
@@ -227,7 +227,9 @@ Every image the pipeline returns is marked as AI-generated in two ways (on by de
 - **An invisible watermark** in the pixels ([invisible-watermark](https://github.com/ShieldMnt/invisible-watermark),
   method `dwtDctSvd`) carrying the fixed payload `AGATE002`. In our tests it survived a PNG round trip, a JPEG
   re-save at quality 90 and a 0.75× resize, and was absent from images Agate did not generate
-  (38 dB PSNR against the unmarked image).
+  (38 dB PSNR against the unmarked image). It is **not recoverable on about 1–2% of outputs**, mostly flat logos on a pure
+  white background, where clipping at white erases the embedded bits (measured on the 120-image test battery of each
+  release, fresh images: 1–2 misses per 120). The metadata still marks those images.
 - **Provenance metadata** in `img.info`: `ai_generated: true`, `generator: Agate Preview 002 (LogoLabs)`,
   `model: Logolabs/agate-preview-002`. Save with `agate.save(img, "out.png")` to keep it as PNG text chunks. The
   prompt and seed are recorded only with `record_prompt=True`.