Upload 2757549/3116433/README.md with huggingface_hub

2757549/3116433/README.md

@@ -0,0 +1,65 @@
+---
+license: other
+tags:
+- concept
+- face
+- faceid
+- ltx
+- t2v
+---
+
+# Best-FaceID - v1.0 - Character Sheet - 3116433
+
+**Model Type**: LORA
+
+**Base Model**: LTXV 2.3
+
+**Trigger Words**: ref_t2v: A [age group] [gender/person] with [skin tone], [hair length, texture, and color], [facial hair or distinctive facial feature], a [face shape] face, and [eye color] eyes, with a [body type] build and [posture], wearing [main clothing, colors, and footwear], working as a [profession, role, or character archetype] inside [location or environment], [shot type].  The subject [first action], [second action], and [third action]. They then [final or concluding action involving an object, character, or environment].  The camera begins [initial camera position or angle], [camera movement], and slowly [final camera movement] as the subject [action performed during the camera movement].  [Role-specific clothing or costume details], [important props or accessories], [lighting style], [visual atmosphere or cinematic mood].
+
+**Tags**: concept, face, faceid, ltx, t2v
+
+## 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=3116433)
+
+Archive: [CivArchive Page](https://civarchive.com/models/2757549?modelVersionId=3116433)
+
+<!-- Version: 20260710_upload -->