model card
Browse files
README.md
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: ByteDance/Bernini-R
|
| 4 |
+
tags: [gguf, wan2.2, comfyui, bernini-r, text-to-video, image-editing]
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
# Bernini-R — GGUF (high / low noise experts)
|
| 8 |
+
|
| 9 |
+
GGUF quantizations of **[ByteDance/Bernini-R](https://huggingface.co/ByteDance/Bernini-R)**
|
| 10 |
+
(Wan2.2-T2V-A14B + source-id RoPE + APG) for use with
|
| 11 |
+
**[ComfyUI-BerniniR](https://github.com/neuregex/ComfyUI-BerniniR)** + `ComfyUI-GGUF`.
|
| 12 |
+
|
| 13 |
+
Two experts (Wan 2.2 high/low-noise), quants: `Q4_K_M`, `Q5_K_M`, `Q8_0`.
|
| 14 |
+
Load each with `UnetLoaderGGUF` then `BerniniR · Apply Patches`. GGUF avoids the fp8
|
| 15 |
+
dual-expert memory crash, so both experts run in 24 GB.
|