{ "name": "Dispatch Style Lora LTX2.3", "slug": "dispatch-style-lora-ltx2-3", "base_model": "LTX-2.3", "media_type": "video", "model_id": 2375591, "version_id": 2776562, "version_name": "LTX 2.3 V1.1", "source": "civitai", "url": "https://civitai.com/models/2375591", "repo_id": null, "file_path": null, "author": "tazmannner379", "category": { "key": "style", "label": "Visual style" }, "modalities": [], "primary_modality": "unspecified", "checkpoint_family": "unknown", "trigger_words": [ "DISPSTYLE", "char_rr", "char_bb", "char_case", "char_invisi", "char_prism", "char_malev", "char_roy", "char_punchup" ], "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 [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 author never states which weight family this targets. 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" ] }, "pros": [ "Well established — 2,212 downloads. [source: CivitAI stats]", "Positively received — 150 thumbs-up with no down-votes. [source: CivitAI stats]", "Explicit trigger word(s) — DISPSTYLE, char_rr, char_bb, char_case, char_invisi, char_prism, char_malev, char_roy, char_punchup — so the effect can be turned on and off from the prompt. [source: model metadata]" ], "cons": [ "Author never states which generation mode it was trained for; test against your own workflow before relying on it. [source: description]", "Large at 1286 MB — slower to load and heavier to stack. [source: file size]" ], "file": { "name": "dispatch23_v1_2-step00031000.comfy.safetensors", "size_bytes": 1348030184, "size_mb": 1285.58, "sha256": "54c9119f9f9f41dca49a00ff734c0020a90b38d1e15e62bca77ed50b84d2e4b6" }, "stats": { "downloads": 2212, "thumbs_up": 150, "thumbs_down": 0 }, "popularity": { "downloads": 2212, "thumbs_up": 150, "thumbs_down": 0, "comments": 17, "approval": "100% positive (150/150)", "age_days": 172.9, "downloads_per_day": 7.67, "rank_by_downloads": 20, "rank_by_momentum": 43, "of_total": 150, "adoption_tier": "High", "momentum": "Steady" }, "selection_score": 4412.0, "selection_reasons": [ "2,212 downloads", "150 thumbs-up", "documented triggers + usage notes", "top-ranked for its category" ], "example_media": [ { "file": "01_video.mp4", "type": "video", "resolution": "1920x1024", "prompt": "", "poster": "01_poster.jpg" }, { "file": "02_video.mp4", "type": "video", "resolution": "1920x1024", "prompt": "", "poster": "02_poster.jpg" }, { "file": "03_video.mp4", "type": "video", "resolution": "1920x1024", "prompt": "", "poster": "03_poster.jpg" }, { "file": "04_video.mp4", "type": "video", "resolution": "1920x1024", "prompt": "", "poster": "04_poster.jpg" }, { "file": "05_video.mp4", "type": "video", "resolution": "1920x1024", "prompt": "", "poster": "05_poster.jpg" }, { "file": "06_video.mp4", "type": "video", "resolution": "1920x1024", "prompt": "", "poster": "06_poster.jpg" } ], "tags": [ "style" ], "scraped_at": "2026-09-05T00:10:48+00:00", "mirror": { "repo_id": "Alex995647/loras-ltxv-2.3", "path_in_repo": "dispatch-style-lora-ltx2-3", "url": "https://huggingface.co/Alex995647/loras-ltxv-2.3/tree/main/dispatch-style-lora-ltx2-3", "local_weights_removed": true, "bytes_freed": 1348030184 }, "path": "ltxv-2.3/dispatch-style-lora-ltx2-3", "archive": { "comments_total": 15, "comments": [ { "author": "9832676", "score": 1, "text": "Fantastic work man, was this trained on musubi trainer the same as before?\nalso are you now doing it with LTX 2.3 checkpoints?\nreally would love your training data <3 dataset.toml + training_args.toml\n\neither im always asking too much or im doing something wrong for my loras.", "created_at": "2026-03-16T08:52:49.054Z" }, { "author": "2355314", "score": 0, "text": "Thanks for the revision and adding in the training data! Gonna have fun with this and cross my fingers for Coupe inclusion some day, thanks again.", "created_at": "2026-03-16T18:15:35.366Z" }, { "author": "114378", "score": 1, "text": "FYI I added some sample captions and videos, plus my settings files in the dataset download zip file.", "created_at": "2026-03-17T00:57:34.228Z" }, { "author": "7045", "score": 0, "text": "Hi! How to make original characters but with this style?", "created_at": "2026-03-22T13:07:57.657Z" }, { "author": "5381509", "score": 0, "text": "The LORA system is extremely impressive. It enables six different roles to interact within a single LORA system while maintaining consistency. This has shown us the potential of LTX2.3. Additionally, I would like to ask you a question. Could you please tell me about the labels of the video training set and the tools you used to complete it? If you can answer, I would be very grateful!", "created_at": "2026-03-23T07:48:38.745Z" }, { "author": "114378", "score": 4, "text": "I think I might do a v2 of this. Try adding more characters and fix the audio quality issue. I think a lower LR on the audio might fix it. Not sure when I'll try, my next lora may a different show", "created_at": "2026-03-26T04:44:45.078Z" }, { "author": "36034", "score": 0, "text": "Works pretty great in a V2V Workflow from a WAN 2.2 input.", "created_at": "2026-04-09T19:32:48.545Z" }, { "author": "2355314", "score": 0, "text": "Been enjoying this, thanks and just wondering if you had any plans to do an update it to H3?", "created_at": "2026-08-19T15:42:26.048Z" } ], "faq": [ { "question": "What is Dispatch Style Lora LTX2.3?", "answer": "Dispatch Style Lora LTX2.3 is a style LoRA designed for LTX Video-family checkpoints, published by [tazmannner379](/users/tazmannner379) on CivitAI in February 2026, now on version 5. It layers on top of any compatible LTX Video checkpoint. You load the checkpoint first, then apply this LoRA on top of it. It has attracted 1,327 downloads. The model is flagged NSFW on CivitAI and can produce explicit content." } ], "trigger_words": [ "DISPSTYLE", "char_rr", "char_bb", "char_case", "char_invisi", "char_prism", "char_malev", "char_roy", "char_punchup" ], "tags": [ "style" ], "rating": 0, "rating_count": 0, "favorite_count": 0, "creator": "tazmannner379", "url": "https://civarchive.com/models/2375591?modelVersionId=2776562" } }