Remove third-party assets, link to original sources

README.md

@@ -29,41 +29,21 @@ Anime image generation that nails anatomy, follows your prompt, and gives you th
 
 **GitHub**: [teenu/4cgt](https://github.com/teenu/4cgt) | **Website**: [4cgt.com](https://4cgt.com) | **Sponsor**: [GitHub Sponsors](https://github.com/sponsors/teenu)
 
-## Assets
+## About
 
-| File | Size | Required |
-|------|------|----------|
-| `NoobAI-XL-Vpred-v1.0.safetensors` | 6.7 GB | Yes |
-| `dora/noobai_vp10_stabilizer_v0.271_fp16.safetensors` | 44 MB | Yes (recommended) |
-| `dora/noobai_vp10_stabilizer_v0.280a_fp16.safetensors` | 64 MB | Yes |
-| `style/*.csv` | 109 MB | Yes |
-| `controlnet/openpose_fp32.safetensors` | 4.7 GB | Optional (pose control) |
-| `poses/*.png` | 140 KB | Optional (examples) |
+This repo hosts showcase images generated by 4CGT. The tool itself lives on [GitHub](https://github.com/teenu/4cgt).
 
-## Quick start
+4CGT requires third-party model assets to run. These are not included here — download them from their original sources:
 
-```bash
-git clone https://github.com/teenu/4cgt.git && cd 4cgt
-pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu124
-pip install -r requirements.txt
+| Asset | Source | License |
+|-------|--------|---------|
+| NoobAI XL V-Pred 1.0 (BF16) | [Laxhar/noobai-XL-Vpred-1.0](https://huggingface.co/Laxhar/noobai-XL-Vpred-1.0) | Fair AI Public License 1.0-SD |
+| DoRA stabilizers (v0.271, v0.280a) | [Civitai: reakaakasky](https://civitai.com/models/971952) | See creator's terms |
+| Style CSVs (Danbooru/e621) | [Laxhar/noob-wiki](https://huggingface.co/datasets/Laxhar/noob-wiki) | Apache-2.0 |
+| ControlNet OpenPose SDXL | [xinsir/controlnet-openpose-sdxl-1.0](https://huggingface.co/xinsir/controlnet-openpose-sdxl-1.0) | Apache-2.0 |
 
-# Download everything from this repo
-pip install huggingface-hub
-huggingface-cli download epigene/4cgt --local-dir assets
-mv assets/NoobAI-XL-Vpred-v1.0.safetensors . && mv assets/dora/* dora/ && mv assets/style/* style/
-rm -rf assets
-
-python main.py
-```
-
-## What makes this different
-
-- **DoRA anatomical stabilizers** eliminate the melted-face lottery. Characters have correct proportions, every time.
-- **600-token prompts** with A1111 weight syntax. Standard CLIP cuts off at 77. 4CGT doesn't.
-- **Same seed = same hash.** Byte-identical output across macOS, Windows, Linux. Not "similar" — identical.
-- **2D to 3D in <1 second.** Integrated Apple Sharp pipeline. Generate, convert to Gaussian Splat, render flythrough video.
-- **Lossless pipeline.** FP16 is rejected on load. BF16/FP32 only. FP32 VAE always.
+See the [GitHub README](https://github.com/teenu/4cgt#assets) for full setup instructions.
 
 ## License
 
-AGPL-3.0. See [GitHub](https://github.com/teenu/4cgt) for details.
+4CGT (the tool) is [AGPL-3.0](https://github.com/teenu/4cgt/blob/main/LICENSE). Third-party assets carry their own licenses — see the table above.