Upload 2757549/3103007/README.md with huggingface_hub

2757549/3103007/README.md

@@ -0,0 +1,74 @@
+---
+license: other
+tags:
+- concept
+- face
+- faceid
+- ltx
+- t2v
+---
+
+# Best-FaceID - v1.0 - 3103007
+
+**Model Type**: LORA
+
+**Base Model**: LTXV 2.3
+
+**Trigger Words**: None
+
+**Tags**: concept, face, faceid, ltx, t2v
+
+## Gallery
+
+<table>
+  <tr>
+    <td><video src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/6cad571c-5096-4f8e-9b42-c31a6796a8ae/original=true/135870807.mp4" width="200" controls muted autoplay loop></video></td>
+    <td><video src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/c8a56c61-a46d-4974-a834-84e173aa1fb1/original=true/135870806.mp4" width="200" controls muted autoplay loop></video></td>
+  </tr>
+</table>
+
+## Description
+
+**LTX-Best-Face-ID — Identity LoRA for LTX-2 (Reference-to-Video)**  
+  
+Keep a person's identity in generated video. Give it **one reference photo** + a text prompt, and  
+it generates a video of that person performing the action.  
+  
+**How it works**  
+  
+The reference is injected as an **overlap** latent with **TASS-RoPE (source-phase)** tagging, plus a  
+differentiable **ArcFace identity loss** — so the face transfers without becoming the first frame.  
+Rank-128 LoRA, trained on **HuMoSet** (close-up / frontal identities). Base model: **LTX-2 (22B)**.  
+  
+⚠️ **Requires the BFS Nodes for ComfyUI**  
+  
+👉 <https://github.com/alisson-anjos/ComfyUI-BFSNodes>
+
+**Full model card + files (workflow)**: <https://huggingface.co/Alissonerdx/LTX-Best-Face-ID>  
+  
+Use the **LTX Identity Transfer** node → feed the reference image → load this LoRA on the MODEL path.  
+  
+**Tips**  
+  
+- Use a **clean, frontal, well-lit close-up** as the reference.  
+- Identity is **prompt-driven** — describe the person's attributes (skin tone, hair, eyes, glasses,  
+facial hair) for best results. The shared workflow's \*\*Prompt Enhancer\*\* can auto-describe the  
+reference for you.  
+- Prefix prompts with `**ref\_t2v**:`.  
+  
+**Limitations**  
+  
+- **Close-up bias** — full-body / large-angle shots hold identity less well.  
+- A bare/generic prompt gives **weaker identity** — describe the person.  
+- The reference framing/accessories can partially **copy** into the video; a clean frontal  
+reference minimizes it.
+
+---
+
+Author: [NRDX](https://civitai.com/user/NRDX)
+
+Model: [CivitAI Model Page](https://civitai.com/models/2757549?modelVersionId=3103007)
+
+Archive: [CivArchive Page](https://civarchive.com/models/2757549?modelVersionId=3103007)
+
+<!-- Version: 20260706_upload -->