Expand model card: VTuber pose-transfer beta docs

README.md

@@ -3,6 +3,7 @@ license: apache-2.0
 language:
 - en
 pipeline_tag: image-to-image
+library_name: pytorch
 tags:
 - image-to-image
 - pose-transfer
@@ -10,4 +11,129 @@ tags:
 - human-pose
 - keypoints
 - diffusion
----
+- vtuber
+- anime
+- real-time
+- windows
+- cuda
+---
+
+# VTM-Elf 0.01
+
+**A from-scratch pose-transfer + image-generation model built for VTubers.**
+
+VTM-Elf takes a live pose (from your camera / skeleton) and renders a character image in that pose. Pose transfer and image generation live in the **same model base** — not a bolted-on ControlNet stack on top of a generic SD checkpoint.
+
+> **Status: Beta**  
+> Image quality is still limited. That is expected at this stage and mostly comes down to **model size** and a **small training dataset** — not a permanent ceiling.
+
+---
+
+## What this model is for
+
+| | |
+|---|---|
+| **Audience** | VTubers / live avatar pipelines |
+| **Task** | Pose transfer → character image |
+| **Input** | Pose (keypoints / skeleton derived from camera) + identity/reference context |
+| **Output** | Character image matching the given pose |
+| **Style** | Anime / VTuber-oriented |
+
+### Pipeline (high level)
+
+```text
+Camera frame
+    ↓
+Skeleton / keypoints
+    ↓
+Pose normalizer  (scale, center, consistent body frame)
+    ↓
+VTM-Elf  (pose-conditioned generation)
+    ↓
+Character image in your pose
+```
+
+The normalizer is important: it averages and remaps joints into a consistent space so the character comes back with **correct proportions / dimensions**, not a warped copy of your raw camera pose.
+
+---
+
+## Getting started
+
+### Requirements (current)
+
+| Requirement | Support |
+|---|---|
+| **OS** | **Windows only** (other platforms not supported yet) |
+| **GPU** | **NVIDIA + CUDA only** |
+| **CPU / macOS / AMD** | Not supported |
+
+If you are not on Windows with an NVIDIA CUDA GPU, this release will not run for you yet.
+
+### Download the weights
+
+```bash
+hf download sinBoo1/VTM-Elf-0.01 VTM-elf.pt-000060000 --local-dir ./VTM-Elf-0.01
+```
+
+Or with Python:
+
+```python
+from huggingface_hub import hf_hub_download
+
+ckpt = hf_hub_download(
+    repo_id="sinBoo1/VTM-Elf-0.01",
+    filename="VTM-elf.pt-000060000",
+)
+print(ckpt)
+```
+
+### Files
+
+| File | Notes |
+|---|---|
+| `VTM-elf.pt-000060000` | Main checkpoint (~436 MB) — step 60k |
+| `README.md` | This model card |
+
+---
+
+## Dataset & quality notes
+
+This model was trained on a **small dedicated VTuber/character dataset**:
+
+- about **1,500 characters**
+- roughly **16–30 images per character**
+
+That scale is the main reason generation quality is still rough in beta, together with the current model size. More data and a larger model should improve fidelity, identity consistency, and overall look over time.
+
+**Please treat outputs as experimental** — fine for testing pose drive and pipeline work, not as a finished production look.
+
+---
+
+## Limitations
+
+- **Beta quality** — soft detail, identity drift, and artifacts can happen
+- **Small dataset** — limited character coverage and pose variety
+- **Windows + NVIDIA CUDA only** for now
+- Not a general-purpose text-to-image model — it is a **pose-driven VTuber renderer**
+
+---
+
+## Intended use
+
+- Live / near-live VTuber pose driving
+- Research and prototyping of pose → character pipelines
+- Building on top of a VTuber-first backbone instead of generic SD pose tools
+
+**Not intended for:** photoreal people generation, production-final art, or non-CUDA / non-Windows setups (yet).
+
+---
+
+## Citation / credit
+
+If you use VTM-Elf in a project, a link back to this repo is appreciated:
+
+[`https://huggingface.co/sinBoo1/VTM-Elf-0.01`](https://huggingface.co/sinBoo1/VTM-Elf-0.01)
+
+---
+
+*Built from scratch for VTubers. Still early — quality will improve with more data and scale.*