Add CrossView IC-LoRA for LTX 2.3 22B

.gitattributes

@@ -456,3 +456,13 @@ stylized-pbr-animation-ltx-2-3/example_images/03_video.mp4 filter=lfs diff=lfs m
 stylized-pbr-animation-ltx-2-3/example_images/04_video.mp4 filter=lfs diff=lfs merge=lfs -text
 stylized-pbr-animation-ltx-2-3/example_images/05_video.mp4 filter=lfs diff=lfs merge=lfs -text
 stylized-pbr-animation-ltx-2-3/example_images/06_video.mp4 filter=lfs diff=lfs merge=lfs -text
+crossview-ic-lora-for-ltx-2-3-22b/example_images/01_poster.jpg filter=lfs diff=lfs merge=lfs -text
+crossview-ic-lora-for-ltx-2-3-22b/example_images/01_video.mp4 filter=lfs diff=lfs merge=lfs -text
+crossview-ic-lora-for-ltx-2-3-22b/example_images/02_poster.jpg filter=lfs diff=lfs merge=lfs -text
+crossview-ic-lora-for-ltx-2-3-22b/example_images/02_video.mp4 filter=lfs diff=lfs merge=lfs -text
+crossview-ic-lora-for-ltx-2-3-22b/example_images/03_poster.jpg filter=lfs diff=lfs merge=lfs -text
+crossview-ic-lora-for-ltx-2-3-22b/example_images/03_video.mp4 filter=lfs diff=lfs merge=lfs -text
+crossview-ic-lora-for-ltx-2-3-22b/example_images/04_poster.jpg filter=lfs diff=lfs merge=lfs -text
+crossview-ic-lora-for-ltx-2-3-22b/example_images/04_video.mp4 filter=lfs diff=lfs merge=lfs -text
+crossview-ic-lora-for-ltx-2-3-22b/example_images/05_poster.jpg filter=lfs diff=lfs merge=lfs -text
+crossview-ic-lora-for-ltx-2-3-22b/example_images/05_video.mp4 filter=lfs diff=lfs merge=lfs -text

crossview-ic-lora-for-ltx-2-3-22b/LTX2.3-22B_IC-LoRA-CrossView-Warp_v2_6000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9796a6e14a8f8fadf0eda6c0ccc6c300c02bd5457fe9a0d4b91ffec39badda3
+size 327287384

crossview-ic-lora-for-ltx-2-3-22b/example_images/01_video.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0621f8f61b1aa48c07c4b4061bf0742b2b048e9dd3dd55be80682a0913016caa
+size 7122633

crossview-ic-lora-for-ltx-2-3-22b/example_images/02_video.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee07586f8ec59c47bb5acc1236027981c0fd1bc46655b39485d7ddb7e3693ad5
+size 1053471

crossview-ic-lora-for-ltx-2-3-22b/example_images/03_video.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cd79675e1f1255c6a5faf5bbd97a04912c22b93df97733c86c25488ce75d8eb
+size 9997490

crossview-ic-lora-for-ltx-2-3-22b/example_images/04_video.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:919911b5f7bfbdb2eabd15293a5ef2dc15826899d9d21b4b57ab66e6a78cd282
+size 8508949

crossview-ic-lora-for-ltx-2-3-22b/example_images/05_video.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e45ddf0935e5fbd1494007e8f21cb2fc92527b92f51e5910c30b08821489d9f1
+size 10398872

crossview-ic-lora-for-ltx-2-3-22b/info.txt

@@ -0,0 +1,369 @@
+═══════════════════════════════════════════════════════════════════════════════
+  CROSSVIEW IC-LORA FOR LTX 2.3 22B
+═══════════════════════════════════════════════════════════════════════════════
+
+───────────────────────────────────────────────────────────────────────────────
+  IDENTITY
+───────────────────────────────────────────────────────────────────────────────
+  Base model        LTX-2.3
+  Generation mode   IC-LoRA / Video-to-Video (V2V)
+  Checkpoint        ltx-2.3-22b-dev (full / base)
+  Category          Speed / step-reduction
+  Author            Cseti
+  Source            https://civitai.com/models/2779316
+  Provenance        CivitAI · model 2779316 · version 3246265
+
+───────────────────────────────────────────────────────────────────────────────
+  WEIGHTS
+───────────────────────────────────────────────────────────────────────────────
+  File              LTX2.3-22B_IC-LoRA-CrossView-Warp_v2_6000.safetensors
+  Version           Warp 2.0
+  Size              312.1 MB
+  Format            SafeTensor / unknown precision
+  SHA256            e9796a6e14a8f8fadf0eda6c0ccc6c300c02bd5457fe9a0d4b91ffec39badda3
+  Published         2026-08-19
+
+───────────────────────────────────────────────────────────────────────────────
+  TRIGGER WORDS
+───────────────────────────────────────────────────────────────────────────────
+  No trigger word. The LoRA applies as soon as it is loaded —
+  strength is the only way to dial the effect up or down.
+
+───────────────────────────────────────────────────────────────────────────────
+  RECOMMENDED SETTINGS
+───────────────────────────────────────────────────────────────────────────────
+  Taken verbatim from the author's description:
+
+  LoRA strength       1.3
+
+───────────────────────────────────────────────────────────────────────────────
+  ADOPTION & POPULARITY
+───────────────────────────────────────────────────────────────────────────────
+  Downloads               840
+  Rating                  100% positive (53/53)
+  Comments                5
+  Published               16 days ago
+  Download rate           8.3/day since release
+
+  Adoption rank           #49 of 150 in this collection  (Moderate)
+  Momentum rank           #41 of 150 by download rate  (Steady · fresh release)
+
+  Adoption tier is the percentile of total downloads within this collection;
+  momentum is the percentile of downloads-per-day since release. Momentum is
+  ranked rather than measured against a fixed rate, because this base model
+  is itself new and every LoRA looks fast on an absolute scale. Both numbers
+  are CivitAI's, read on the scrape date at the foot of this file.
+
+───────────────────────────────────────────────────────────────────────────────
+  CHAINING / STACKING
+───────────────────────────────────────────────────────────────────────────────
+  Stacks with others      not stated
+
+  The author gave no chaining guidance. The rules below are the
+  general LTX-2.3 ones, not anything specific to this LoRA.
+
+  General LTX-2.3 rules that apply here (see REFERENCE.txt):
+
+  • Stacking an acceleration LoRA with a task LoRA is officially
+    sanctioned: the ID-LoRA template chains LoraLoaderModelOnly(ltx_2.3_22b
+    _distilled_1.1_lora_dynamic_fro09_avg_rank_111_bf16, 0.5) into
+    LoraLoaderModelOnly(ltx-2.3-id-lora-talkvid-3k, 1.0) on the dev
+    checkpoint.
+  • The Python CLI exposes `--lora <path> [strength]` as a repeatable flag
+    with default strength 1.0, so multiple adapters at once is a supported
+    configuration, not a hack.
+  • Load the acceleration/distilled LoRA on the dev checkpoint only. The
+    two-stage pipelines require it for the full model but explicitly do not
+    use it for DistilledPipeline, ICLoraPipeline or DubItPipeline, which
+    already run distilled weights.
+  • Do not stack two distillation LoRAs (e.g. the official rank-384 /
+    rank-111 one plus a community DMD LoRA). The DaSiWa DMD LoRA already
+    blends 75-80% of the official distilled delta into its audio-output
+    route and is described by its author as recreating the distilled model
+    on top of stock dev, i.e. a replacement.
+  • IC-LoRAs are not chained like ordinary LoRAs: each carries a
+    reference_downscale_factor in its safetensors metadata and needs a node
+    that reads it (GetICLoRAParameters -> LTXVAddGuide in core, or
+    LTXICLoRALoaderModelOnly + LTXAddVideoICLoRAGuide in ComfyUI-LTXVideo).
+    Without one the factor silently defaults to 1.
+  • Two IC-LoRA reference guides can be driven from a single IC-LoRA: the
+    CrossView Warp author wires both a depth-warp video and the original
+    video into separate reference guides and sets latent_downscale_factor =
+    1 on both.
+  • DubItPipeline accepts exactly one Dub-It IC-LoRA (`--lora` exactly
+    once) and applies it in both stages — that path is single-adapter by
+    design.
+  • Community convention on strengths when stacking: the IC-LoRA Dual-
+    Character author recommends 0.6-1.0 for a content LoRA used alone,
+    dropped to 0.3-0.5 when combined with others.
+  • Some LoRA pairs are designed to be blended against each other — the LTX
+    2.3 Crisp Enhance / Soft Enhance pair is described by its author as
+    "can be used together and balanced at different strengths".
+  • The gemma-3-12b-it-abliterated LoRA is not a video LoRA and does not
+    belong in the DiT chain — it patches the Gemma text encoder through a
+    model+clip LoraLoader, as the official templates wire it.
+  • The step-reduction adapter for LTX-2.3 is first-party. Lightricks
+    publishes ltx-2.3-22b-distilled-lora-384.safetensors and
+    ltx-2.3-22b-distilled-lora-384-1.1.safetensors (rank 384, 7.61 GB each,
+    verified from the HF file listing), described in the model card as "A
+    LoRA version of the distilled model applicable to the full model" —
+    apply it to ltx-2.3-22b-dev and the model runs the distilled 8-step,
+    CFG=1 schedule. Comfy-Org additionally ships a dynamically rank-reduced
+    repack, ltx_2.3_22b_distilled_1.1_lora_dynamic_fro09_avg_rank_111_bf16.
+    safetensors (2.74 GB), and this is the file every offic
+  • The full, flexible, trainable bf16 model — ltx-2.3-22b-dev.safetensors
+    is 46.15 GB bf16, 29.15 GB as ltx-2.3-22b-dev-fp8.safetensors. This is
+    what LoRAs are trained against, and what four of the six official
+    ComfyUI LTX-2.3 templates load (t2v, i2v, ia2v, id_lora). Needs either
+    real guidance (Lightricks' own single-stage workflow sets LTXVScheduler
+    to 15 steps with MultimodalGuider) or the distill
+
+───────────────────────────────────────────────────────────────────────────────
+  PROS
+───────────────────────────────────────────────────────────────────────────────
+  + Positively received — 53 thumbs-up with no down-votes. [source: CivitAI
+    stats]
+  + Compact at 312 MB — cheap to stack with other LoRAs. [source: file
+    size]
+  + Author published concrete recommended settings. [source: description]
+
+───────────────────────────────────────────────────────────────────────────────
+  CONS & CAVEATS
+───────────────────────────────────────────────────────────────────────────────
+  - Has a stated dependency — read the author's description before loading.
+    [source: description]
+  - No trigger word — the LoRA is always on once loaded, so strength is the
+    only control. [source: model metadata]
+  - Modest adoption (840 downloads) — less community feedback to rely on.
+    [source: CivitAI stats]
+
+───────────────────────────────────────────────────────────────────────────────
+  COMPATIBILITY WARNING
+───────────────────────────────────────────────────────────────────────────────
+  Within LTX-2.3, dev vs distilled is low risk: they are the same
+  architecture and the distillation itself is published as a LoRA that the
+  model card calls "applicable to the full model", so ordinary content LoRAs
+  load on both. Expect style/strength drift rather than breakage; the
+  distilled LoRA is meant to be applied to a dev checkpoint, not stacked on
+  an already-distilled one (the Python pipelines that start from a distilled
+  checkpoint — DistilledPipeline, ICLoraPipeline, DubItPipeline — explicitly
+  do not take --distilled-lora). The genuine risk is cross-version and cross-
+  format, and it is silent rather than a hard error: the LTX-2 repo README
+  states flatly that files "are not interchangeable between the two models,
+  and a LoRA only works with the model it was trained on", and a wrong-
+  version LoRA surfaces only as a stream of "lora key not loaded:
+  diffusion_model...." console warnings while generation proceeds as if no
+  LoRA were attached. The same silent no-op hits correctly-versioned LoRAs
+  saved in a non-ComfyUI key layout: SimpleTuner issue #2349 shows keys like
+  diffusion_model.connectors.audio_connector.transformer_blocks.N.attn1.to_q
+  going unloaded, where the LTX-2 trainer's own layout is attn1/attn2 for
+  video, audio_attn1/audio_attn2 for audio and audio_to_video_attn /
+  video_to_audio_attn for cross-modal. Community finetunes (Sulphur 2, JoyAI-
+  Echo merges) load stock LTX-2.3 LoRAs but shift the result. And an IC-LoRA
+  loaded without a metadata-reading node loses its reference scale: ComfyUI's
+  GetICLoRAParameters reads reference_downscale_factor out of the LoRA's
+  safetensors metadata and silently falls back to 1 when it is absent, so a
+  ref0.5 IC-LoRA wired straight into LTXVAddGuide without it feeds the
+  reference at the wrong latent scale.
+
+───────────────────────────────────────────────────────────────────────────────
+  AUTHOR'S DESCRIPTION
+───────────────────────────────────────────────────────────────────────────────
+  LTX-Video 2.3 22B — IC-LoRA: CrossView
+  V2 version of the CrossView Warp LoRA is out I've been working a lot on
+  this one. I hope you'll like it. You can find more details about the
+  training, inference, limitations in the Huggingface repo:
+  https://huggingface.co/Cseti/LTX2.3-22B_IC-LoRA-CrossView-Warp_v2
+  Warp version What it does: you give it a video and a camera offset (azimuth
+  / elevation / distance), and it generates the same scene from that new
+  viewpoint. It's an IC-LoRA for LTX-Video 2.3 (22B) with two reference
+  videos: a depth-warp of your video (this carries the geometry) and the
+  original video itself (this keeps the identity). The warps come from the
+  CrossViewWarp ComfyUI node, which uses Depth Anything V2 input.
+  KEYFRAME UPDATE: The offset doesn't have to be a single fixed pose. Right-
+  clicking the node's 3D orbit picker drops keyframes, and it interpolates a
+  camera pose per frame — so instead of a new static viewpoint you can drive
+  a whole camera move (an orbit around the subject) across the clip.
+  Unlike my CrossView Prompt LoRA (which takes the camera angle from a text
+  prompt), this one takes the angle as numbers — so you can set the viewpoint
+  precisely instead of choosing from a fixed phrase list.
+  Important : The Warp version requires a custom ComfyUI node (you can find
+  the link below). The Prompt version doesn't.
+  You can download
+  - the required ComfyUI preprocessing node from here:
+  https://github.com/cseti007/ComfyUI-CrossViewWarp
+
+  - the example workflow from here:
+  https://huggingface.co/datasets/Cseti/ComfyUI-
+  Workflows/tree/main/ltx/2.3/ic-lora-crossview-warp
+
+  Usage (ComfyUI) Install the ComfyUI-CrossViewWarp custom node (clone into
+  ComfyUI/custom_nodes/, install its requirements, restart ComfyUI). It needs
+  the Depth Anything V2 node for the depth input.
+  - Load LTX2.3-22B_IC-LoRA-CrossView-Warp_v0.9_18000.safetensors as the IC-
+  LoRA.
+
+  - Wire your input video to both the CrossViewWarp node (frames + DA-V2
+  depth) and an IC-LoRA reference guide. The node's warp output goes to a
+  second reference guide. Set latent_downscale_factor = 1 on both guides.
+
+  - Set the camera on the node — either with the numbers or by dragging the
+  camera marker on the built-in 3D orbit picker widget.
+
+  Important: Unfortunately distance setting doesn't work as expected due to
+  some dataset problems which will be solved in the next release.
+  Settings that worked for me
+  - IC-LoRA strength: 1.3
+
+  - Both IC-LoRA guides: latent_downscale_factor = 1
+
+  - For distance > 1: describe the revealed content in the prompt (see in
+  "limitations" below)
+
+  Limitations - It steers the viewpoint, it doesn't reproject it. The model
+  treats the warp as a hint and re-imagines the scene from the new angle. You
+  often get a smaller rotation than you asked for.
+
+  - Pulling the camera back (distance > 1) often does nothing on its own.
+  What helped: describe the unseen parts in the prompt. If you want a
+  character shown from farther away, write out the clothing and body details
+  that weren't visible in the source ("full-body shot, knee-high leather
+  boots, long dark skirt"). The prompt fills in what the warp can't know.
+
+  Prompt version A fine-tuned In-Context LoRA (IC-LoRA) adapter for LTX-Video
+  2.3 (22B) that acts as a virtual second camera : give it a reference video
+  and a short camera-angle prompt, and it re-renders the same scene from the
+  requested new viewpoint keeping the subject and content, changing where the
+  camera stands.
+  v0.9 — proof-of-concept. Trained on synthetic multi-view data; it
+  generalizes to real footage but has clear limits (see Limitations).
+  Feedback welcome.
+  Usage (ComfyUI) I tested this LoRA only in ComfyUI , in a video-to-video
+  (IC-LoRA) workflow. An example workflow is here:
+  https://huggingface.co/datasets/Cseti/ComfyUI-
+  Workflows/blob/main/ltx/2.3/ic-lora-crossview-v1-pilot/README.md
+  How it works:
+  - Load LTX2.3-22B_IC-LoRA-CrossView-Prompt_v0.9_13700.safetensors as the
+  LoRA.
+
+  - Provide a reference video — the scene you want to re-shoot from a new
+  angle.
+
+  - Provide a camera-angle prompt (see the vocabulary below). No starting
+  image is needed
+
+  Prompt vocabulary (important) Unlike a free-text LoRA, this model was
+  trained on a fixed, discrete camera vocabulary . Every prompt must start
+  with the trigger crossview. followed by the template:
+  crossview. new camera angle: {azimuth}, {elevation}, {distance}.
+  All 63 valid combinations are listed in captions_all_63.txt in my
+  Huggingface repo. Use these exact phrases — the model learned this
+  vocabulary specifically, so synonyms ("45 degrees left", "slightly
+  leftward") work less reliably.
+  Example prompts:
+  crossview. new camera angle: to the right, lower, closer.
+  crossview. new camera angle: to the left, higher, further.
+  crossview. new camera angle: same angle, same height, closer.
+  Tips - Angle size & chaining: the model works most reliably on small,
+  single-step angle changes . For a larger viewpoint shift, chain several
+  small steps — feed the generated view back in as the new reference and
+  apply another small angle.
+
+  - Full prompt list: every prompt used to train this model is in
+  captions_all_63.txt — use these exact phrases.
+
+  - Distilled model: the LoRA was trained on the full (non-distilled)
+  LTX-2.3. On distilled few-step workflows its effect is weaker — try a LoRA
+  strength of 1.2–1.5 , and/or run it in the first (non-distilled) pass.
+
+  Training and dataset details This IC-LoRA was trained on RunPod cloud GPUs
+  (NVIDIA RTX PRO 6000 Blackwell, 96 GB).
+  Detailed information about the training parameters and used dataset can be
+  found under my HF repo: https://huggingface.co/Cseti/LTX2.3-22B_IC-LoRA-
+  CrossView-Prompt
+  Limitations - Viewpoint range: the training cameras span a frontal sector
+  (~±60° azimuth max) — "view from behind" is out of range.
+
+  - Distilled model: weaker on distilled few-step models (see Tips).
+
+  License This LoRA is shared under the Apache License 2.0 . It was trained
+  entirely on the SynCamVideo dataset, which is itself Apache-2.0 licensed,
+  so the training data places no additional restrictions on this adapter and
+  it can be released under the same permissive terms.
+  Note: using this LoRA requires the LTX-Video 2.3 base model, which is
+  governed by its own license — please review Lightricks' terms for the base
+  weights separately.
+  Support Producing and sharing this kind of open-source work requires
+  renting cloud GPUs, which gets expensive quickly. If you find it useful and
+  would like me to keep contributing, your support is very much appreciated:
+
+───────────────────────────────────────────────────────────────────────────────
+  EXAMPLE MEDIA
+─────────────────��─────────────────────────────────────────────────────────────
+  5 preview(s) in ./example_images/ — community results for
+  this LoRA. Videos keep a matching _poster.jpg still frame.
+
+  No prompts are recorded below: CivitAI's public API flags these posts as
+  having generation metadata but does not return it, so the prompts cannot be
+  scraped. Open the model page to read them.
+
+  01_video.mp4  (video, 2444x1156)
+      still: 01_poster.jpg
+  02_video.mp4  (video, 1344x768)
+      still: 02_poster.jpg
+  03_video.mp4  (video, 2444x1156)
+      still: 03_poster.jpg
+  04_video.mp4  (video, 2498x1188)
+      still: 04_poster.jpg
+  05_video.mp4  (video, 2562x1132)
+      still: 05_poster.jpg
+
+───────────────────────────────────────────────────────────────────────────────
+  HOW TO USE (COMFYUI)
+───────────────────────────────────────────────────────────────────────────────
+  1. Update ComfyUI. LTX-2.3 is supported in ComfyUI core
+  (comfy_extras/nodes_lt.py provides EmptyLTXVLatentVideo, LTXVAddGuide,
+  GetICLoRAParameters, LTXVConditioning, LTXVScheduler,
+  LTXVConcatAVLatent/LTXVSeparateAVLatent, LTXVReferenceAudio and more) and
+  the six official templates need no custom nodes; install the Lightricks
+  "ComfyUI-LTXVideo" custom node pack only if you want IC-LoRA loaders, low-
+  VRAM loaders, HDR decode, audio-only nodes or Q8 nodes.
+  2. Put the base checkpoint in ComfyUI/models/checkpoints/ —
+  ltx-2.3-22b-dev-fp8.safetensors (29.15 GB) or ltx-2.3-22b-distilled-
+  fp8.safetensors (29.53 GB) from Lightricks/LTX-2.3-fp8, or the bf16
+  originals (46.15 GB) from Lightricks/LTX-2.3. It is a single file that also
+  carries the video VAE, the audio VAE and the text projection.
+  3. Put gemma_3_12B_it_fp4_mixed.safetensors in
+  ComfyUI/models/text_encoders/ (from Comfy-Org/ltx-2). The Python package
+  instead wants the full google/gemma-3-12b-it-qat-q4_0-unquantized folder.
+  4. Put ltx-2.3-spatial-upscaler-x2-1.1.safetensors in
+  ComfyUI/models/latent_upscale_models/ (needed by every two-stage template),
+  and moge_2_vitl_normal_fp16.safetensors (Comfy-Org/MoGe) in
+  ComfyUI/models/geometry_estimation/ if you use the IC-LoRA depth path.
+  5. Put every LoRA .safetensors in ComfyUI/models/loras/. Subfolders are
+  fine — Lightricks' own workflows reference
+  "ltxv/ltx2/ltx-2.3-22b-distilled-lora-384-1.1.safetensors".
+  6. Load a normal content/style LoRA with LoraLoaderModelOnly, wired between
+  CheckpointLoaderSimple's MODEL output and the guider/sampler. In the stock
+  templates you chain it after the distilled-LoRA loader. Use the full
+  LoraLoader (model + clip) only for the gemma-3-12b-it-abliterated LoRA,
+  which patches the Gemma text encoder rather than the video model.
+  7. On a dev checkpoint, also load the acceleration LoRA
+  (ltx_2.3_22b_distilled_1.1_lora_dynamic_fro09_avg_rank_111_bf16.safetensors
+  at 0.5) unless you intend to run the slow guided path.
+  8. For an IC-LoRA, the LoRA loader alone is not enough: either use
+  LTXICLoRALoaderModelOnly + LTXAddVideoICLoRAGuide (ComfyUI-LTXVideo), or —
+  as the official ic_lora template does — feed the LoRA-loaded model through
+  core's GetICLoRAParameters into LTXVAddGuide, so the
+  reference_downscale_factor stored in the file's safetensors metadata is
+  read instead of defaulting to 1.
+  9. Template Library > Video > any LTX-2.3 workflow gives you correct wiring
+  to start from; workflow JSONs are at Comfy-Org/workflow_templates/templates
+  /video_ltx2_3_{t2v,i2v,ia2v,flf2v,ic_lora,id_lora}.json and
+  Lightricks/ComfyUI-LTXVideo/example_workflows/2.3/.
+
+───────────────────────────────────────────────────────────────────────────────
+  Scraped by lorakit on 2026-09-04 23:17 UTC.
+  Stats and description are the author's; pros/cons are derived from the
+  evidence tagged beside each line.
+───────────────────────────────────────────────────────────────────────────────

crossview-ic-lora-for-ltx-2-3-22b/metadata.json

@@ -0,0 +1,139 @@
+{
+  "name": "CrossView IC-LoRA for LTX 2.3 22B",
+  "slug": "crossview-ic-lora-for-ltx-2-3-22b",
+  "base_model": "LTX-2.3",
+  "media_type": "video",
+  "model_id": 2779316,
+  "version_id": 3246265,
+  "version_name": "Warp 2.0",
+  "source": "civitai",
+  "url": "https://civitai.com/models/2779316",
+  "repo_id": null,
+  "file_path": null,
+  "author": "Cseti",
+  "category": {
+    "key": "accelerator",
+    "label": "Speed / step-reduction"
+  },
+  "modalities": [
+    "v2v_ic_lora"
+  ],
+  "primary_modality": "v2v_ic_lora",
+  "checkpoint_family": "dev",
+  "trigger_words": [],
+  "recommended_settings": {
+    "LoRA strength": "1.3"
+  },
+  "chaining": {
+    "author": {
+      "stacks": "not stated",
+      "notes": "",
+      "avoid": [],
+      "requires": [],
+      "order": "",
+      "strength": "",
+      "stated": false
+    },
+    "general_rules": [
+      "Stacking an acceleration LoRA with a task LoRA is officially sanctioned: the ID-LoRA template chains LoraLoaderModelOnly(ltx_2.3_22b_distilled_1.1_lora_dynamic_fro09_avg_rank_111_bf16, 0.5) into LoraLoaderModelOnly(ltx-2.3-id-lora-talkvid-3k, 1.0) on the dev checkpoint.",
+      "The Python CLI exposes `--lora <path> [strength]` as a repeatable flag with default strength 1.0, so multiple adapters at once is a supported configuration, not a hack.",
+      "Load the acceleration/distilled LoRA on the dev checkpoint only. The two-stage pipelines require it for the full model but explicitly do not use it for DistilledPipeline, ICLoraPipeline or DubItPipeline, which already run distilled weights.",
+      "Do not stack two distillation LoRAs (e.g. the official rank-384 / rank-111 one plus a community DMD LoRA). The DaSiWa DMD LoRA already blends 75-80% of the official distilled delta into its audio-output route and is described by its author as recreating the distilled model on top of stock dev, i.e. a replacement.",
+      "IC-LoRAs are not chained like ordinary LoRAs: each carries a reference_downscale_factor in its safetensors metadata and needs a node that reads it (GetICLoRAParameters -> LTXVAddGuide in core, or LTXICLoRALoaderModelOnly + LTXAddVideoICLoRAGuide in ComfyUI-LTXVideo). Without one the factor silently defaults to 1.",
+      "Two IC-LoRA reference guides can be driven from a single IC-LoRA: the CrossView Warp author wires both a depth-warp video and the original video into separate reference guides and sets latent_downscale_factor = 1 on both.",
+      "DubItPipeline accepts exactly one Dub-It IC-LoRA (`--lora` exactly once) and applies it in both stages — that path is single-adapter by design.",
+      "Community convention on strengths when stacking: the IC-LoRA Dual-Character author recommends 0.6-1.0 for a content LoRA used alone, dropped to 0.3-0.5 when combined with others.",
+      "Some LoRA pairs are designed to be blended against each other — the LTX 2.3 Crisp Enhance / Soft Enhance pair is described by its author as \"can be used together and balanced at different strengths\".",
+      "The gemma-3-12b-it-abliterated LoRA is not a video LoRA and does not belong in the DiT chain — it patches the Gemma text encoder through a model+clip LoraLoader, as the official templates wire it.",
+      "The step-reduction adapter for LTX-2.3 is first-party. Lightricks publishes ltx-2.3-22b-distilled-lora-384.safetensors and ltx-2.3-22b-distilled-lora-384-1.1.safetensors (rank 384, 7.61 GB each, verified from the HF file listing), described in the model card as \"A LoRA version of the distilled model applicable to the full model\" — apply it to ltx-2.3-22b-dev and the model runs the distilled 8-step, CFG=1 schedule. Comfy-Org additionally ships a dynamically rank-reduced repack, ltx_2.3_22b_distilled_1.1_lora_dynamic_fro09_avg_rank_111_bf16.safetensors (2.74 GB), and this is the file every offic",
+      "The full, flexible, trainable bf16 model — ltx-2.3-22b-dev.safetensors is 46.15 GB bf16, 29.15 GB as ltx-2.3-22b-dev-fp8.safetensors. This is what LoRAs are trained against, and what four of the six official ComfyUI LTX-2.3 templates load (t2v, i2v, ia2v, id_lora). Needs either real guidance (Lightricks' own single-stage workflow sets LTXVScheduler to 15 steps with MultimodalGuider) or the distill"
+    ]
+  },
+  "pros": [
+    "Positively received — 53 thumbs-up with no down-votes. [source: CivitAI stats]",
+    "Compact at 312 MB — cheap to stack with other LoRAs. [source: file size]",
+    "Author published concrete recommended settings. [source: description]"
+  ],
+  "cons": [
+    "Has a stated dependency — read the author's description before loading. [source: description]",
+    "No trigger word — the LoRA is always on once loaded, so strength is the only control. [source: model metadata]",
+    "Modest adoption (840 downloads) — less community feedback to rely on. [source: CivitAI stats]"
+  ],
+  "file": {
+    "name": "LTX2.3-22B_IC-LoRA-CrossView-Warp_v2_6000.safetensors",
+    "size_bytes": 327287384,
+    "size_mb": 312.13,
+    "sha256": "e9796a6e14a8f8fadf0eda6c0ccc6c300c02bd5457fe9a0d4b91ffec39badda3"
+  },
+  "stats": {
+    "downloads": 840,
+    "thumbs_up": 53,
+    "thumbs_down": 0
+  },
+  "popularity": {
+    "downloads": 840,
+    "thumbs_up": 53,
+    "thumbs_down": 0,
+    "comments": 5,
+    "approval": "100% positive (53/53)",
+    "age_days": 16.1,
+    "downloads_per_day": 8.3,
+    "rank_by_downloads": 49,
+    "rank_by_momentum": 41,
+    "of_total": 150,
+    "adoption_tier": "Moderate",
+    "momentum": "Steady · fresh release"
+  },
+  "selection_score": 1476.0,
+  "selection_reasons": [
+    "840 downloads",
+    "53 thumbs-up",
+    "top-ranked for its category"
+  ],
+  "example_media": [
+    {
+      "file": "01_video.mp4",
+      "type": "video",
+      "resolution": "2444x1156",
+      "prompt": "",
+      "poster": "01_poster.jpg"
+    },
+    {
+      "file": "02_video.mp4",
+      "type": "video",
+      "resolution": "1344x768",
+      "prompt": "",
+      "poster": "02_poster.jpg"
+    },
+    {
+      "file": "03_video.mp4",
+      "type": "video",
+      "resolution": "2444x1156",
+      "prompt": "",
+      "poster": "03_poster.jpg"
+    },
+    {
+      "file": "04_video.mp4",
+      "type": "video",
+      "resolution": "2498x1188",
+      "prompt": "",
+      "poster": "04_poster.jpg"
+    },
+    {
+      "file": "05_video.mp4",
+      "type": "video",
+      "resolution": "2562x1132",
+      "prompt": "",
+      "poster": "05_poster.jpg"
+    }
+  ],
+  "tags": [
+    "camera",
+    "lora",
+    "ltx",
+    "tool",
+    "control"
+  ],
+  "scraped_at": "2026-09-04T23:17:52+00:00",
+  "path": "ltxv-2.3/crossview-ic-lora-for-ltx-2-3-22b"
+}