CivArchive
    Best-FaceID - v1.0 - Character Sheet
    NSFW

    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.

    Description

    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 - 4 Views | Flux.2 Klein LoRA | Civitai). You can use this LoRa to generate the 4 views, the Lora image that generates 3 views has better quality, so maybe you could combine the close-up from the 4-view image with the 3 views from the 3 views lora, haha. Remembering that the image resolution needs to be 1536x1024.

    FAQ

    Comments (26)

    ArtiOtakuJul 11, 2026· 1 reaction
    CivitAI

    Thanks so much for the character sheet lora! Should we use a sheet exactly formatted like yours, or can it take any type of sheets?

    NRDX
    Author
    Jul 11, 2026· 1 reaction

    In my dataset, I only had sheets in this format. You can test other formats, but I recommend using the same one as mine; it's easy to generate in the GPT chat.

    ArtiOtakuJul 11, 2026· 1 reaction

    @NRDX yeah, looks like a simple and direct character sheet, I'll follow this format then, thanks!

    sonofabeanJul 11, 2026

    @ArtiOtaku The creator of this Lora has one for Flux Klein that generates these exact sheets

    ArtiOtakuJul 11, 2026

    @sonofabean Nice, I already deleted all my Flux models after Krea2 came out, though, so, i guess I'll have to rely on ChatGPT for this.

    ayyylmao32213Jul 11, 2026
    CivitAI

    so i can't just add this as a lora in wan2gp and expect it to work right?

    NRDX
    Author
    Jul 12, 2026

    You can try using it as i2v, but it will cause your reference frame to become the first frame of the video, and it won't just be used as a reference. To work with Wangp, I believe you would have to take my BFS node and adapt it for Wangp.

    AI_SleestakJul 14, 2026· 1 reaction

    Try using it and a reference image in the Control Video/Frames Injection - Ingredients Reference Sheet section. For me it seemed to work MUCH stronger with this LORA to keep the identity locked in to the reference image. Maybe a bit too much - with a face that was highly matching the expression of the reference. Needs more testing/tweaking, but I think that's a good place to strt in WanGP. BTW I'm using version 12.3 of WanGP

    smereces_aiJul 15, 2026
    CivitAI

    it works, but limited only one character!!! :(

    NRDX
    Author
    Jul 15, 2026

    Yes, it's only 1 character, I never said it works with more than 1.

    NRDX
    Author
    Jul 15, 2026

    But I'll try training a multi-ref LoRa, so in theory it would be possible to use it with more than one.

    GT123Jul 16, 2026
    CivitAI

    Why are characters always off-center and on the sides ?

    NRDX
    Author
    Jul 16, 2026

    Give me an example? But anyway, you can write the prompt freely, define the position in the prompt. If that doesn't solve it, it could be a bias in the dataset based on humo.

    GT123Jul 16, 2026

    @NRDX thanks for the replay,i add a video below,in the prompt i already add " keep the man always in the center of the frame"

    FullMetal1111Jul 16, 2026

    It will be center when use 1024x1024.

    KnoxxxonkJul 16, 2026
    CivitAI

    works nice but having 1 issue i could use advice on. given the character sheet is a landscape image, if i want to create a portrait video (no control) and ref_size_mode is set to native then the subject is always off center to the left, like the latent is rendering a landscape ratio and then cropping but left aligned. however if is witch it to match_ref then it fixes this issue, but then i think the character sheet is getting cropped because it loses the face detail in the result. is there a way to use the character sheet but make a portrait video without these issues?

    KnoxxxonkJul 16, 2026

    i pretty much lose likeness in all settings ive tried unless its set to native_resolution, which again seems to be a left aligned cropped video if the reference image is a different ratio than the video

    NRDX
    Author
    Jul 17, 2026· 1 reaction

    @Knoxxxonk Good catch, thanks for the detailed report — dug into it and there are actually two separate things going on:

    match_target losing face detail: this mode resizes the reference to the output's pixel size via a center-crop first, then resize (not a stretch). So when the reference is a landscape character sheet and the output is portre sheet away before resizing — if the face closeup panel isn'tdead-center in your sheet layout, it gets cut off entirely. That's the "loses face detail" you're seeing.

    native_resolution off-center-left: this encodes the ref at its own native (landscape) size regardless of the output's aspect ratio. Since the training data always used a fixed landscape canvas for the reference sheet, the model likely never learned to reconcile a landscape reference with a portrait output cleanly — it seems to "compose" as if landscape, and what you get is bastion cropped left-aligned into the portrait canvas. That one'smore of a training-data-coverage limitation than a pure bug.

    Fix: just pushed v1.10.13 with a new ref_resize_mode option: match_target_letterbox. It resizes to the output's pixel size like match_target, but fits the whole reference inside it preserving aspect ratio (no crop at all), padding the leftover space with white instead of cutting anything off. You'll get some white bars on the sides/top-bottom depending on your sheet's asp you'll never lose reference content — should fix the face-detailloss without reintroducing the off-center issue.

    Try match_target_letterbox for mismatched aspect ratios (portrair vice versa) — that's the mode I'd recommend for your case.Update the node pack and it should show up in the dropdown.

    KnoxxxonkJul 17, 2026

    @NRDX will give it a shot tomorrow but have one quality concern. Did you update it so it uses the actual size of the output? For example my video size will be 544x960. If the character sheet from your lora which is like 1546 or something in width has to scale down to 544 width and still have all 4 reference squeezed in there, we will lose a lot of resolution.

    NRDX
    Author
    Jul 17, 2026

    @Knoxxxonk In the case of the character sheet, there's not much I can do; I'll have to see what's possible.

    KnoxxxonkJul 17, 2026

    @NRDX i tried it and i didnt see much of a difference using the letter box approach. the content was centered but the likeness still dropped.
    i reorganized my character sheet to match the portrait ratio with the close up in the top left, top right front, side in bottom left and back in bottom right and just keeping native res it did help a little but still offset, just not as much. still the offset is a bit too much. if this can get resolved this workflow would be awesome

    FullMetal1111Jul 16, 2026· 1 reaction
    CivitAI

    The character sheet video, camera always shifts to upper left when I generate low res video like 512x512. I use LTX Identity Transerfer node with native res. It looks like strictly fix to some video resolution like 1024x1024 or 1536x1024. Is there any way to fix this problem without need to increase video resolution?

    KnoxxxonkJul 17, 2026· 1 reaction

    i am having the same issue as per my comment just a few hours before yours. the OP made a fix but it doesnt seem to make much difference for me, it still is docks the result left aligned and unless i use native res it simply doesnt keep the likeness since internally it is being cropped, even with the new letterbox setting. my thing is im trying to do portrait and the character sheet is landscape.
    i restructured my character sheet to be the same portrait ratio 9:16 and made the close up in the top left, front top right, side bottom left and back bottom right. it seems to help a little bit but everything is still slightly shifted to the left its just not as bad.

    FullMetal1111Jul 17, 2026

    We're in the same boat. Hope NRDX fix our boat soon.

    NRDX
    Author
    Jul 17, 2026· 3 reactions

    The only way to fix this would be to train in a way that the reference is actually offset relative to the empty latents; in this case, it would be using st-drc, which is an approach I haven't yet managed to get working 100%, but I'll look into it.

    randombrowser1234Jul 25, 2026
    CivitAI

    Hi, Im a lazy noob with no time to train my own character sheet.

    What does Best_FaceID_CharacterSheet_v1.0_LoRA.safetensors

    actually contain ? Is it data specific to one of your personal models that you're providing as an example ? Will it morph my input image character into yours ? (Which I dont want it to) or can this file still help to preserve my input character's ID without me having to train my own character sheet ?

    LORA
    LTXV 2.3
    by NRDX

    Details

    Downloads
    687
    Platform
    CivitAI
    Platform Status
    Available
    Created
    7/10/2026
    Updated
    7/27/2026
    Deleted
    -
    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].