Organisation card: LogoLabs, Inkvec, Agate, LogoBrief-10K

README.md

@@ -1,10 +1,74 @@
 ---
 title: README
-emoji: 🌍
-colorFrom: indigo
-colorTo: red
+colorFrom: gray
+colorTo: yellow
 sdk: static
 pinned: false
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# LogoLabs
+
+LogoLabs is a branding and logo design company that works from data. We study what makes a
+mark work: how brands are drawn, what their briefs ask for, and which choices hold up. Then
+we design identities on that evidence rather than on taste alone.
+
+The research behind that work is open. Here you'll find the models, tools and datasets we
+build it on: generating marks, turning them into clean vector files, and understanding what
+makes a design brief. The tools run on your own machine or in your browser, and nothing you
+draw or type is sent anywhere.
+
+**For an identity designed to a higher standard than any open tool can give you,** visit
+[logolabs.org](https://logolabs.org) or [contact us](https://logolabs.org/contact).
+
+## Inkvec: raster to SVG, exactly
+
+[**Inkvec**](https://github.com/logolabs/inkvec) is an open-source (Apache-2.0) vectoriser
+that turns a PNG, JPEG or WebP logo into a clean SVG. It fits every shape by minimum
+description length: edges placed to a fraction of a pixel, the fewest curves that match
+the image, gradients kept as gradients, and transparency traced as it is. In our published
+comparison it has the lowest colour error on every case against VTracer and Trazor, and a
+Fast mode trades a little of that precision for speed.
+
+- **Try it in the browser:** [Inkvec Studio Lite](https://huggingface.co/spaces/Logolabs/inkvec),
+  the full editor as WebAssembly, with before-and-after comparisons on real logos.
+- **Desktop app and command line** for Windows, macOS and Linux:
+  [releases](https://github.com/logolabs/inkvec/releases).
+- **Bindings** for Python, JavaScript, Go, Swift, Java, .NET, PHP and C, all generated from
+  one options schema.
+
+Two small models ship with it, and are released on their own too:
+
+| Model | What it does | Size | Licence |
+|---|---|---|---|
+| [inkvec-denoiser-001](https://huggingface.co/Logolabs/inkvec-denoiser-001) | Removes JPEG, WebP and AI-decoder damage from flat artwork before tracing | 19.7M | Apache-2.0 |
+| [inkvec-sr-001](https://huggingface.co/Logolabs/inkvec-sr-001) | 4x super-resolution for logos and icons (MambaIRv2-Small, fine-tuned) | 9.77M | Apache-2.0 |
+
+## Agate: a compact text-to-image model
+
+[**Agate Preview 001**](https://huggingface.co/Logolabs/agate-preview-001) is a
+260M-parameter text-to-image model trained from scratch in 145 GPU-hours. It scores 0.550
+on GenEval with the official scorer, level with SDXL's published 0.55, and runs in under two
+seconds on a consumer GPU (MIT).
+
+- **Try it in the browser:** [Agate WebGPU](https://huggingface.co/spaces/Logolabs/agate-webgpu),
+  where the whole model runs on your own GPU; prompts never leave your machine.
+- **ComfyUI:** the [agate-comfyui](https://github.com/logolabs/agate-comfyui) node pack.
+
+## LogoBrief-10K: a dataset of logos and their briefs
+
+[**LogoBrief-10K**](https://huggingface.co/datasets/Logolabs/LogoBrief-10K) is 10,000 brand
+logos, each with its original SVG and a clean raster render, plus design annotations:
+open-vocabulary style tags, a one-sentence motif description, a full generated design brief,
+and text-region bounding boxes. Domains are sampled by web-popularity rank rather than picked
+for recognisable brands, and every one was checked for AI-training opt-out signals before
+publication. Access is gated; the card's preview images are in
+[LogoBrief-10K-assets](https://huggingface.co/datasets/Logolabs/LogoBrief-10K-assets).
+
+## Compute
+
+Our models were trained on **Arrhenius** at NAISS, through **EuroHPC JU**.
+
+## Links
+
+[logolabs.org](https://logolabs.org) · [Contact](https://logolabs.org/contact) ·
+[GitHub](https://github.com/logolabs) · [Inkvec documentation](https://logolabs.github.io/inkvec)