Upload README.md with huggingface_hub

README.md

@@ -1,15 +1,51 @@
 ---
 license: apache-2.0
 base_model: ByteDance/Bernini-R
-tags: [gguf, wan2.2, comfyui, bernini-r, text-to-video, image-editing]
+pipeline_tag: text-to-video
+library_name: gguf
+tags:
+  - gguf
+  - wan2.2
+  - comfyui
+  - bernini-r
+  - text-to-video
+  - image-editing
+  - video-editing
 ---
 
-# Bernini-R — GGUF (high / low noise experts)
+# Bernini-R — GGUF (high & low noise experts)
+
+**[💻 Code / ComfyUI nodes](https://github.com/neuregex/ComfyUI-BerniniR)** · **[💬 Discord — updates, roadmaps, projects, or just to chat](https://discord.gg/HxfP9TnctJ)** · **[🧬 Bernini-R](https://huggingface.co/ByteDance/Bernini-R)** · **[Wan2.2-T2V-A14B](https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B)**
 
 GGUF quantizations of **[ByteDance/Bernini-R](https://huggingface.co/ByteDance/Bernini-R)**
-(Wan2.2-T2V-A14B + source-id RoPE + APG) for use with
-**[ComfyUI-BerniniR](https://github.com/neuregex/ComfyUI-BerniniR)** + `ComfyUI-GGUF`.
+(= Wan2.2-T2V-A14B + source-id RoPE + multi-condition APG guidance), for use in ComfyUI with
+**[ComfyUI-BerniniR](https://github.com/neuregex/ComfyUI-BerniniR)** + [`city96/ComfyUI-GGUF`](https://github.com/city96/ComfyUI-GGUF).
+
+Bernini-R is a **dual-expert** model (Wan 2.2): a high-noise expert sets the composition and a
+low-noise expert refines detail. Both are quantized here. GGUF carries no fp8 tensors, so the two
+experts coexist in **24 GB VRAM** without the offload crash the fp8 build hits.
+
+## Files
+
+| File | Expert | Quant | Size |
+|------|--------|-------|------|
+| `bernini_r_high_noise_14B-Q4_K_M.gguf` | high-noise | Q4_K_M | 9.66 GB |
+| `bernini_r_high_noise_14B-Q5_K_M.gguf` | high-noise | Q5_K_M | 10.8 GB |
+| `bernini_r_high_noise_14B-Q8_0.gguf`   | high-noise | Q8_0   | 15.4 GB |
+| `bernini_r_low_noise_14B-Q4_K_M.gguf`  | low-noise  | Q4_K_M | 9.66 GB |
+| `bernini_r_low_noise_14B-Q5_K_M.gguf`  | low-noise  | Q5_K_M | 10.8 GB |
+| `bernini_r_low_noise_14B-Q8_0.gguf`    | low-noise  | Q8_0   | 15.4 GB |
+
+`Q5_K_M` is the recommended balance; `Q8_0` for best quality, `Q4_K_M` for the lowest VRAM.
+
+## Usage in ComfyUI
+
+1. Install **[ComfyUI-BerniniR](https://github.com/neuregex/ComfyUI-BerniniR)** and **[ComfyUI-GGUF](https://github.com/city96/ComfyUI-GGUF)**.
+2. Put the `.gguf` files in `ComfyUI/models/unet/`. You also need the Wan VAE (`wan_2.1_vae.safetensors`) and the UMT5 text encoder (`umt5_xxl_fp8_e4m3fn_scaled.safetensors`).
+3. **t2v / t2i** (`source_id=0` is identical to stock Wan 2.2): one `UnetLoaderGGUF` → your sampler.
+4. **Editing (i2i / v2v), both experts:** load each GGUF with `UnetLoaderGGUF`, send each through
+   **BerniniR · Apply Patches**, then into **BerniniR · Guider** (`model` = high, `model_low` = low).
+   The guider switches expert by timestep (t=875) and runs the APG guidance.
+   Ready-made graph: `workflows/ui/bernini_i2i_gguf_dual.json` in the node repo.
 
-Two experts (Wan 2.2 high/low-noise), quants: `Q4_K_M`, `Q5_K_M`, `Q8_0`.
-Load each with `UnetLoaderGGUF` then `BerniniR · Apply Patches`. GGUF avoids the fp8
-dual-expert memory crash, so both experts run in 24 GB.
+License: Apache-2.0 (same as the base model).