Add LTX2.3-AI anime style

.gitattributes

@@ -487,3 +487,13 @@ ltx2-3-frozen-elsa/example_images/03_video.mp4 filter=lfs diff=lfs merge=lfs -te
 ltx2-3-frozen-elsa/example_images/04_video.mp4 filter=lfs diff=lfs merge=lfs -text
 ltx2-3-frozen-elsa/example_images/05_video.mp4 filter=lfs diff=lfs merge=lfs -text
 ltx2-3-frozen-elsa/example_images/06_video.mp4 filter=lfs diff=lfs merge=lfs -text
+ltx2-3-ai-anime-style/example_images/01_video.mp4 filter=lfs diff=lfs merge=lfs -text
+ltx2-3-ai-anime-style/example_images/02_poster.jpg filter=lfs diff=lfs merge=lfs -text
+ltx2-3-ai-anime-style/example_images/02_video.mp4 filter=lfs diff=lfs merge=lfs -text
+ltx2-3-ai-anime-style/example_images/03_poster.jpg filter=lfs diff=lfs merge=lfs -text
+ltx2-3-ai-anime-style/example_images/03_video.mp4 filter=lfs diff=lfs merge=lfs -text
+ltx2-3-ai-anime-style/example_images/04_poster.jpg filter=lfs diff=lfs merge=lfs -text
+ltx2-3-ai-anime-style/example_images/04_video.mp4 filter=lfs diff=lfs merge=lfs -text
+ltx2-3-ai-anime-style/example_images/05_poster.jpg filter=lfs diff=lfs merge=lfs -text
+ltx2-3-ai-anime-style/example_images/05_video.mp4 filter=lfs diff=lfs merge=lfs -text
+ltx2-3-ai-anime-style/example_images/06_video.mp4 filter=lfs diff=lfs merge=lfs -text

ltx2-3-ai-anime-style/example_images/01_video.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66c0198d6c89d34d4bfc646fb868903ac1b7aae731491119913726b4c4042edb
+size 9101873

ltx2-3-ai-anime-style/example_images/02_video.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b21e1d22ba4e1d03031b2e4b040b8d3694b118be91bf0523577e7518a7313cf1
+size 14757719

ltx2-3-ai-anime-style/example_images/03_video.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95b5f5f365dcfcec297b3748a923bc75e006a25216300ee30accedb3794c0b6d
+size 22977779

ltx2-3-ai-anime-style/example_images/04_video.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ced655363905ef58de9e3c55b81b4c223ced73369735c2db601aee62479ff75
+size 12943725

ltx2-3-ai-anime-style/example_images/05_video.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f1903c1ffe10a12b6362f4b8e5248826bc853a27cf9a486403a149ce412331e
+size 13602327

ltx2-3-ai-anime-style/example_images/06_video.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e8b5fc65dd354df16430a76ea16b9b701b512c352b7efeb813e86987493c56d
+size 11934159

ltx2-3-ai-anime-style/h-anime4.comfy.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76b2308ab069cf48ac71636467814739b9723613eb724dadd3c14aa70ce43044
+size 855972872

ltx2-3-ai-anime-style/info.txt

@@ -0,0 +1,336 @@
+═══════════════════════════════════════════════════════════════════════════════
+  LTX2.3-AI ANIME STYLE
+═══════════════════════════════════════════════════════════════════════════════
+
+───────────────────────────────────────────────────────────────────────────────
+  IDENTITY
+───────────────────────────────────────────────────────────────────────────────
+  Base model        LTX-2.3
+  Generation mode   Text-to-Video (T2V)
+  Checkpoint        ltx-2.3-22b-dev (full / base)
+  Category          Visual style
+  Author            liao942287300dog
+  Source            https://civitai.com/models/2725065
+  Provenance        CivitAI · model 2725065 · version 3062850
+
+───────────────────────────────────────────────────────────────────────────────
+  WEIGHTS
+───────────────────────────────────────────────────────────────────────────────
+  File              h-anime4.comfy.safetensors
+  Version           AI-anime-v1.0
+  Size              816.3 MB
+  Format            SafeTensor / unknown precision
+  SHA256            76b2308ab069cf48ac71636467814739b9723613eb724dadd3c14aa70ce43044
+  Published         2026-06-23
+
+───────────────────────────────────────────────────────────────────────────────
+  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
+───────────────────────────────────────────────────────────────────────────────
+  The author did not publish specific settings.
+  No author settings were published. Community baseline: steps Distilled path
+  (all six official ComfyUI LTX-2.3 templates): 8 steps in stage 1 driven by
+  an explicit ManualSigmas list "1.0, 0.99375, 0.9875, 0.98125, 0.975,
+  0.909375, 0.725, 0.421875, 0.0", then 3 steps in the stage-2 refine after
+  the x2 latent upscale ("0.85, 0.7250, 0.4219, 0.0") — verified by reading
+  the template JSONs. The ic_lora template instead uses a plain KSampler at 8
+  steps. The Python DistilledPipeline is documented as "8 predefined sigmas
+  (8 steps in stage 1, 4 steps in stage 2)". Full/dev model with real
+  guidance: Lightricks' own single-stage example workflow sets LTXVScheduler
+  to 15 steps., cfg 1.0 for anything running the distilled checkpoint or the
+  distilled LoRA — CFGGuider is set to 1 in both stages of every official
+  ComfyUI template (verified in the JSONs), the ic_lora template's KSampler
+  is cfg 1, and a note in Lightricks' own two- stage workflow reads "Do
+  explore various samplers and cfg values (although we advise them to be kept
+  close to 1)". For the guided full-model path, Lightricks' single-stage
+  workflow uses MultimodalGuider with per-modality GuiderParameters: VIDEO
+  cfg 3 (rescale 0.9), AUDIO cfg 7 (rescale 0.7). Treat 3 as the video anchor
+  since that is the official value., sampler euler with SamplerCustomAdvanced
+  + ManualSigmas is the default in the ComfyUI templates; the flf2v template
+  uses SamplerEulerAncestral and the ic_lora template a plain KSampler with
+  euler_ancestral + linear_quadratic. Lightricks' own example workflows use
+  euler_ancestral_cfg_pp (single stage) and euler_cfg_pp (two stage).
+  TI2VidTwoStagesHQPipeline swaps in the second-order res_2s sampler for
+  fewer steps., resolution Generate low, then upscale. ComfyUI templates set
+  EmptyLTXVLatentVideo to 768x512 / 97 frames and target 1280x720 (with a
+  1920x1088 resize and a 1536-long-edge resize in the chain), using
+  LTXVLatentUpsampler with ltx-2.3-spatial- upscaler-x2-1.1.safetensors.
+  Lightricks' own example workflows use 960x544 / 121 frames with the same x2
+  upscaler. Hard constraints from the model card: width and height must be
+  divisible by 32, and frame count must be divisible by 8 plus 1 (97, 121,
+  193...). Frame rate: LTXVConditioning is 24 in the t2v/id_lora templates
+  and 25 in the ic_lora/flf2v templates; CreateVideo is 24 in the ComfyUI
+  templates. The x2 temporal upscaler is described in the model card as being
+  for higher FPS., lora_strength Official distilled/acceleration LoRA: 0.5 in
+  every ComfyUI template (LoraLoaderModelOnly), 0.5 plus a 0.2 second branch
+  in Lightricks' single- stage example workflow, and 0.8 in the ltx-pipelines
+  README/installation CLI example (--distilled-lora <path> 0.8). Official IC-
+  LoRA Union-Control and ID-LoRA: 1.0 in the templates. Community norm for
+  content/style LoRAs: the IC-LoRA Dual-Character author states 0.6-1.0 used
+  alone, dropped to 0.3-0.5 when stacked with other LoRAs..
+
+───────────────────────────────────────────────────────────────────────────────
+  ADOPTION & POPULARITY
+───────────────────────────────────────────────────────────────────────────────
+  Downloads               925
+  Rating                  100% positive (39/39)
+  Comments                0
+  Published               73 days ago
+  Download rate           12.6/day since release
+
+  Adoption rank           #47 of 150 in this collection  (Moderate)
+  Momentum rank           #23 of 150 by download rate  (Trending)
+
+  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 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
+───────────────────────────────────────────────────────────────────────────────
+  (none recorded)
+
+───────────────────────────────────────────────────────────────────────────────
+  CONS & CAVEATS
+───────────────────────────────────────────────────────────────────────────────
+  - No trigger word — the LoRA is always on once loaded, so strength is the
+    only control. [source: model metadata]
+  - Large at 816 MB — slower to load and heavier to stack. [source: file
+    size]
+  - Modest adoption (925 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
+───────────────────────────────────────────────────────────────────────────────
+  This is an anime-style LoRA trained for 40,000 steps with 36 ten-second
+  videos and 98 images. It does not feature a conventional anime aesthetic,
+  and its training dataset was also AI-generated. trigger words：highly
+  polished anime style
+  这是一个动漫风格的lora，使用36个10秒视频和98张图片训练了4W步，这并不是传统意义上的动漫风格，训练集也是由AI产生的。触发词：highly
+  polished anime style
+  如果你不想浪费代理流量，可以去我的夸克网盘下载： https://pan.quark.cn/s/1762c716b213
+  如果你想要出好的的结果的话尽量对动漫人物描述详细一些下面我将例举一些文生视频的提示词例子：
+  If you want to get high-quality results, try to describe anime characters
+  in greater detail. Below I will list some examples of text-to-video
+  prompts:
+  1：
+  highly polished anime style， The camera stays fixed, adopting the first-
+  person perspective of a young man sitting by the window. On the right side
+  of the frame sits a girl with long lavender hair, wearing a white hoodie
+  printed with a black "x" on the chest and a pink pleated skirt. She sits
+  sideways, holding a cup of milk tea in both hands, gazing out the window at
+  the snow scenery. The streets outside the window are covered in snow,
+  several trees stand bare, and buildings can be seen in the distance.
+  The girl slowly turns her head to look at the young man (the first-person
+  perspective) on the left side of the frame, a hint of anticipation and
+  confusion shining in her eyes. Her lips part slightly as if whispering the
+  question, "What am I to you?" Her expression is calm and focused.
+  After the young man in the first-person view replies, "You are my U-Loveit
+  milk tea," the girl’s expression instantly turns slightly confused and
+  playful. She tilts her head a little and blinks, seemingly processing the
+  meaning of his words, then murmurs softly, "So I’m just milk tea?"
+  The young man from the first-person perspective then goes on to say, "That
+  way I can hold you in the palm of my hand."
+  2：
+  Highly refined anime art style. In the scene stands a young girl with short
+  black hair and black cat ears, wearing a white top decorated with a large
+  blue bow tie and striped cuffs. The background is a bright school corridor
+  with windows, and tiny light specks float in the air. She gently presses
+  the index finger of her right hand against her lower lip, gazing forward
+  with soft, slightly bashful eyes and faint blushes on her cheeks, singing
+  Miduo Mountain Ballad with deep affection.
+  3：
+  The video opens in a bright, cozy café rendered in a highly polished anime
+  art style. The frame first shows a medium close-up of two young women
+  sitting side by side at a wooden table.
+  Part 1: The Start of the Conversation
+  Girl 1: A young woman with short silver-grey hair, dressed in a grey
+  windbreaker and a dark red plaid scarf. She wears a slightly melancholy
+  expression, tilting her head slightly to gaze at her friend beside her.
+  Girl 2: A young woman with long black hair, clad in an elegant black
+  uniform paired with a black-and-white polka-dot bow tie and ornate long
+  dangling earrings. She leans forward toward Girl 1, her eyes brimming with
+  curiosity and concern.
+  Actions & Lines: Girl 1 murmurs softly, "I got dumped last night..." A
+  faint tremor lingers in her voice. Right afterward, Girl 2’s eyes fly wide
+  open, her face lighting up with intense excitement as she exclaims,
+  "Really!"
+  Part 2: A Shift in Mood
+  Focus Shot: The camera briefly locks onto Girl 1’s face. Her brows crease
+  faintly, and her eyes dart away, seemingly caught off guard or embarrassed
+  by Girl 2’s reaction.
+  Actions & Lines: She mumbles under her breath, "...Forget I said that..."
+  attempting to mask her feelings.
+  Part 3: The Final Exchange
+  Two-Shot: The shot cuts back to a two-person frame of the pair. Girl 2’s
+  excitement fades into disappointment; she lets out a helpless sigh, leans
+  back in her seat, and looks at Girl 1, asking, "Aww, why though~~"
+  Closing Freeze Frame: Toward the end of the video, the camera slowly zooms
+  in before freezing on Girl 1’s face, which holds a hint of surprise mixed
+  with quiet relief—as if her friend’s words have just amused her, or she has
+  finally resolved to open up her heart.
+
+───────────────────────────────────────────────────────────────────────────────
+  EXAMPLE MEDIA
+───────────────────────────────────────────────────────────────────────────────
+  6 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, 1280x704)
+      still: 01_poster.jpg
+  02_video.mp4  (video, 768x1248)
+      still: 02_poster.jpg
+  03_video.mp4  (video, 736x1312)
+      still: 03_poster.jpg
+  04_video.mp4  (video, 832x1152)
+      still: 04_poster.jpg
+  05_video.mp4  (video, 704x1408)
+      still: 05_poster.jpg
+  06_video.mp4  (video, 704x1280)
+      still: 06_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 23:18 UTC.
+  Stats and description are the author's; pros/cons are derived from the
+  evidence tagged beside each line.
+───────────────────────────────────────────────────────────────────────────────

ltx2-3-ai-anime-style/metadata.json

@@ -0,0 +1,135 @@
+{
+  "name": "LTX2.3-AI anime style",
+  "slug": "ltx2-3-ai-anime-style",
+  "base_model": "LTX-2.3",
+  "media_type": "video",
+  "model_id": 2725065,
+  "version_id": 3062850,
+  "version_name": "AI-anime-v1.0",
+  "source": "civitai",
+  "url": "https://civitai.com/models/2725065",
+  "repo_id": null,
+  "file_path": null,
+  "author": "liao942287300dog",
+  "category": {
+    "key": "style",
+    "label": "Visual style"
+  },
+  "modalities": [
+    "t2v"
+  ],
+  "primary_modality": "t2v",
+  "checkpoint_family": "dev",
+  "trigger_words": [],
+  "recommended_settings": {},
+  "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 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": [],
+  "cons": [
+    "No trigger word — the LoRA is always on once loaded, so strength is the only control. [source: model metadata]",
+    "Large at 816 MB — slower to load and heavier to stack. [source: file size]",
+    "Modest adoption (925 downloads) — less community feedback to rely on. [source: CivitAI stats]"
+  ],
+  "file": {
+    "name": "h-anime4.comfy.safetensors",
+    "size_bytes": 855972872,
+    "size_mb": 816.32,
+    "sha256": "76b2308ab069cf48ac71636467814739b9723613eb724dadd3c14aa70ce43044"
+  },
+  "stats": {
+    "downloads": 925,
+    "thumbs_up": 39,
+    "thumbs_down": 0
+  },
+  "popularity": {
+    "downloads": 925,
+    "thumbs_up": 39,
+    "thumbs_down": 0,
+    "comments": 0,
+    "approval": "100% positive (39/39)",
+    "age_days": 73.2,
+    "downloads_per_day": 12.63,
+    "rank_by_downloads": 47,
+    "rank_by_momentum": 23,
+    "of_total": 150,
+    "adoption_tier": "Moderate",
+    "momentum": "Trending"
+  },
+  "selection_score": 1393.0,
+  "selection_reasons": [
+    "925 downloads",
+    "39 thumbs-up",
+    "top-ranked for its category"
+  ],
+  "example_media": [
+    {
+      "file": "01_video.mp4",
+      "type": "video",
+      "resolution": "1280x704",
+      "prompt": "",
+      "poster": "01_poster.jpg"
+    },
+    {
+      "file": "02_video.mp4",
+      "type": "video",
+      "resolution": "768x1248",
+      "prompt": "",
+      "poster": "02_poster.jpg"
+    },
+    {
+      "file": "03_video.mp4",
+      "type": "video",
+      "resolution": "736x1312",
+      "prompt": "",
+      "poster": "03_poster.jpg"
+    },
+    {
+      "file": "04_video.mp4",
+      "type": "video",
+      "resolution": "832x1152",
+      "prompt": "",
+      "poster": "04_poster.jpg"
+    },
+    {
+      "file": "05_video.mp4",
+      "type": "video",
+      "resolution": "704x1408",
+      "prompt": "",
+      "poster": "05_poster.jpg"
+    },
+    {
+      "file": "06_video.mp4",
+      "type": "video",
+      "resolution": "704x1280",
+      "prompt": "",
+      "poster": "06_poster.jpg"
+    }
+  ],
+  "tags": [
+    "style"
+  ],
+  "scraped_at": "2026-09-04T23:18:10+00:00",
+  "path": "ltxv-2.3/ltx2-3-ai-anime-style"
+}