Best-FaceID

세부 정보

파일 다운로드 (2)

이 버전에 대해

You can use both Loras together, set the base FaceID to 0.2 strength to force a bit more similarity, workflows and more details are on HuggingFace.

To generate the Character Sheet, you can use the GPT Image 2, or any other tool. I also made a model for Flux Klein 9b (TripleView - v1.0 | Flux.2 Klein LoRA | Civitai) that only generates the 3 views (front, side, and back) but doesn't add the Closeup. You can use this LoRa to generate the 3 views and then concatenate the image you used to generate the 3 views as a closeup, remembering that the image resolution needs to be 1536x1024.

모델 설명

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.

If this model was helpful to you in any way, please consider helping me continue creating more model for the price of a coffee.

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.

이 모델로 만든 이미지

정렬

모델 유형	LORA
기본 모델	LTXV 2.3
게시일	2026-07-10
학습된 단어	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].