Awesome LTX-2

A curated list of models, text encoders, and tools for the LTX-2 video generation suite.

Table of Contents

• Apps & Tools
• Models
  • Checkpoints
    • silveroxides Quantizations (mxfp8)
    • Distilled LoRA
    • TenStrip Distilled LoRA Experiments
    • Spatial Upscaler
    • Temporal Upscaler
  • Merges
  • Finetunes
    • DaSiWa
    • 10Eros
    • Sulphur-2-base
    • PinkCherry NSFW
  • GGUF Quantized Models
• Text Encoders
  • Comfy-Org Optimized Encoders
  • Gemma-3-12b Abliterated
  • Gemma-3-12b IT Heretic
• Separated Components
  • Diffusion Models (Transformer Only)
  • VAE (Video & Audio)
  • Embedding Connectors & Text Projection
• LoRA
  • Enchancer, special
  • Styles
  • Special
  • ID-LoRA (Identity-Driven In-Context LoRA)
• ComfyUI Nodes
  • Custom Node Collections
• LoRA Training
  • Primary Local Training Tools
  • Cloud Training Platforms
  • Essential Dataset & Captioning Tools
  • Training Requirements Summary
• Workflow & Technical Notes
  • RuneXX
  • Lightricks
  • vrgamedevgirl84
  • ComfyUI

Intro

• LTX official Blog
• ComfyUI official blogpost
• Prompting Guide for LTX-2
• LTX-2 in ComfyUI Chattable KB

▓ Apps & Tools

LTX2.3-Multifunctional

LTX2.3-Multifunctional is a desktop-optimized version of LTX that lowers GPU requirements and simplifies usage. It integrates all features including image-to-video, text-to-video, start/end frames, lip-sync, video enhancement, and image generation into a single application.

Key Features:

• Lower GPU Requirements: Only needs 24GB VRAM (vs 32GB for standard desktop version)
• All-in-One Interface: No complex ComfyUI workflows or error-prone nodes
• Features: T2V, I2V, start/end frames, lip-sync, video enhancement, image generation, LoRA support
• Multi-Frame Insertion: Two modes for generating long videos
• Easy Setup: No third-party software required, just install LTX desktop

Downloads & Resources:

• HuggingFace | GitHub | ComfyUI Node | Tutorial

O2noor LTX-2.5 Int4 Tile-Train (Beta)

O2noor LTX-2.5 Int4 Tile-Train is a ComfyUI node pack for LoRA training on LTX-2.5 22B distilled using tiled training across multiple GPUs with as little as 18 GB VRAM per card. The base is fully self-contained quantized weights (bnb-NF4 DiT, Gemma-4-12b text encoder — run in 8-bit LLM.int8 spread over 2 GPUs during captioning only, freed for training; works on 12 GB cards).

Downloads & Resources:

• Node pack (GitHub) | Model weights (HF) — includes ltx-2.5-22b-distilled-bnb-nf4 (10.45 GB), embeddings_processor_bf16 (6.34 GB), gemma4-12b-with-proj-ltx-2.5-bf16 (26.26 GB), video + audio VAEs, plus int2 experimental variants

elismasilva LTX 2 Image Custom Blocks (Modular Diffusers)

Custom Modular Diffusers blocks that extend LTX 2 Image (elismasilva's image-only LTX-2.3) with image-to-image, plus a unified AutoBlocks pipeline that folds t2i and i2i into one — the workflow is chosen automatically from the inputs you pass (prompt → text-to-image; prompt + image → image-to-image with optional strength). Code-only repo (trust_remote_code); loads components from the ltx2.3-image-base weights repo. Apache-2.0.

Downloads & Resources:

• Custom blocks (HF) | Image-only checkpoints: ltx2.3-image-comfyui (ComfyUI) · ltx2.3-image-base (diffusers)

WanGP LTX-2 Model Pack (DeepBeepMeep)

The complete set of LTX-2 / 2.3 / 2.5 weights used by WanGP — DeepBeepMeep's low-VRAM video app (down to ~6 GB VRAM, old-GPU friendly, auto-downloads the model variant matching your architecture). 169 files, ~984 GB total, pre-packaged so no manual ComfyUI file layout is needed.

What's inside:

• Main transformers (repo root) — LTX-2.5 22B dev / distilled in bf16 (38.0 GB), int8-convrot (19.5 GB) and nvfp4 (14.7 GB); LTX-2.3 22B dev / distilled / distilled-1.1 bf16 (38.0 GB) plus quanto bf16-int8 (19.5 GB) and nvfp4 (13.5 GB); LTX-2 19B dev / distilled full (43.3 GB), fp8 (27.1 GB), fp4 (20.0 GB) and diffusion-model variants; Q4_K_M / Q6_K / Q8_0 "light" GGUFs (13.0–20.6 GB)
• Third-party audio models — JoyAI-Echo (bf16 + quanto), Scenema, DramaBox, ltx23_echoVid-ltxAud_surgical_fp8, plus Kokoro TTS, Seed-VC, Whisper, HuBERT, BigVGAN, Sherpa
• Shared / offloadable components — video + audio embeddings connectors (bf16 / int8-convrot / nvfp4), text embedding projection, video + audio VAEs, vocoder, spatial and temporal upscalers x2
• Text encoders — both gemma4-12b-ltx-v1 for LTX-2.5 (bf16 23.8 GB / int8-convrot 12.9 GB) and gemma-3-12b-it-qat-q4_0 for LTX-2 / 2.3 (24.4 GB + quanto 13.2 GB)
• LoRAs — LTX-2.5 IC-LoRAs (refine-details, ingredients, SDR-To-HDR + its scene-emb, deblur, decompression, pixel-spatial-upscaler), LTX-2.3 IC-LoRAs (ingredients, in-outpainting, outpaint, refocus, uncompress, ungrade, HDR + scene-emb, union-control, pixel-spatial-upscaler, detailer), LTX-2 IC-LoRAs (detailer, union-control, canny/depth/pose control), distilled-lora-450 / -384, celebvhq ID-LoRAs (LTX-2 and 2.3), Edit-Anything reference, Licon-MSR (2.3 V1/V2, 2.5 V1 + slot embeddings), VBVR-I2V, OmniNFT RL-LoRAs
• Manifest — LTX-2.5-MANIFEST.md documents the LTX-2.5 runtime set, incl. the note that Dev/Distilled connectors are shared only after equality verification and the official NVFP4 transformer needs its own BF16 connector pair

Downloads & Resources:

• WanGP (GitHub) | Model pack (HF)

▓ Models

LTX-2 models are available in various formats including full weights, transformers-only, and GGUF quantizations for efficient inference.

▣ Checkpoints

• Lightricks/LTX-2 - Official repository.
• Lightricks/LTX-2.3 - Official repository (latest version).
• Drbaph - Quantization

Quantized to fp8_e5m2 to support older Triton with older Pytorch on 30 series GPUs. For WangGP in Pinokio

· · · · · · · · · · · · · ·

❖ Image-only LTX-2.3 (text-to-image)

Image-only LTX-2.3 checkpoints by elismasilva — the 13B LTX-2.3 family pruned to the still-image generation path (video/audio weights removed), packaged as unified ComfyUI safetensors. Inherits the LTX Video 2 Open Source License.

· · · · · · · · · · · · · ·

❖ silveroxides Quantizations (mxfp8)

Note: The mxfp8mixed quantization requires a custom fork of ComfyUI-Kitchen with mxfp8 support. Standard ComfyUI installations may not support this quantization format.

· · · · · · · · · · · · · ·

❖ Distilled LoRA

· · · · · · · · · · · · · ·

❖ TenStrip Distilled LoRA Experiments

Experimental distilled LoRAs optimized for finetunes and I2V workflows. These LoRAs avoid the issues of the massive rank 384 official LoRA which can be counterproductive with conditioned inputs and finetunes.

Notes:

• Lower rank LoRAs (72 and below) can be used at 1.0 strength safely for I2V first pass, with upscale pass at 0.4-0.5 strength
• _ceil suffix indicates the dynamic ceiling during reranking
• _condsafe suffix indicates cross-attention and other conditioning layers have been zeroed for better I2V compatibility
• The official rank 384 LoRA can actively dampen conditioning signals in I2V workflows; cond_safe versions work much better

Download All LoRAs

· · · · · · · · · · · · · ·

❖ Spatial Upscaler

Required for current two-stage pipeline implementations in this repository. Download to COMFYUI_ROOT_FOLDER/models/latent_upscale_models folder.

· · · · · · · · · · · · · ·

❖ Temporal Upscaler

Required for current two-stage pipeline implementations in this repository. Download to COMFYUI_ROOT_FOLDER/models/latent_upscale_models folder.

══════════════════════════════════

▣ Merges

Custom merged models combining multiple control signals or specialized configurations.

══════════════════════════════════

▣ Finetunes

Community finetuned models based on LTX-2.3 with specialized improvements and optimizations. Each finetune family may include a backbone checkpoint, low-VRAM component splits, GGUF quants, and merged or extracted LoRAs. Variant cell links go directly to the resolve/main safetensors/gguf file when a single canonical asset covers the row.

❖ DaSiWa

High-performance LoRA-integrated checkpoint family based on LTX 2.3. Includes distilled (4-step) and non-distilled (20-30 step) variants. Recommended sampler: Euler + Simple/Normal/Linear_Quadratic.

DaSiWa extracted LoRA:

· · · · · · · · · · · · · ·

❖ 10Eros

I2V-optimised merge using layer scaled merges at different steps. Not a straight weight merge — behaves much nicer than standard LoRA loading and respects prompts.

◦ Version-Testing repo is gated manual — TenStrip/LTX2.3-10Eros_Version-Testing needs an approved access request (not instant auto-approve), and the README is locked. The beta6 builds above supersede the earlier beta3 / "TURBO-hybrid" entry; the repo also bundles a b6_Rq_Sampling_Nodes.png reference for its RQ sampling nodes.

◦ 10Eros GGUF — vantagewithai low-VRAM quants

vantagewithai/LTX2.3-10Eros-GGUF

vantagewithai/LTX2.3-10Eros-GGUF — v1

Quant	Size	Download
![Q3_K_M][badge-Q3_K_M]	10.36 GB	![vantagewithai][gh-vantagewithai]
![Q3_K_S][badge-Q3_K_S]	9.63 GB	![vantagewithai][gh-vantagewithai]
![Q4_0][badge-Q4_0]	12.09 GB	![vantagewithai][gh-vantagewithai]
![Q4_1][badge-Q4_1]	12.95 GB	![vantagewithai][gh-vantagewithai]
![Q4_K_M][badge-Q4_K_M]	13.31 GB	![vantagewithai][gh-vantagewithai]
![Q4_K_S][badge-Q4_K_S]	12.29 GB	![vantagewithai][gh-vantagewithai]
![Q5_0][badge-Q5_0]	14.21 GB	![vantagewithai][gh-vantagewithai]
![Q5_1][badge-Q5_1]	15.07 GB	![vantagewithai][gh-vantagewithai]
![Q5_K_M][badge-Q5_K_M]	15.03 GB	![vantagewithai][gh-vantagewithai]
![Q5_K_S][badge-Q5_K_S]	14.01 GB	![vantagewithai][gh-vantagewithai]
![Q6_K][badge-Q6_K]	16.55 GB	![vantagewithai][gh-vantagewithai]
![Q8_0][badge-Q8_0]	21.19 GB	![vantagewithai][gh-vantagewithai]

vantagewithai/LTX2.3-10Eros-1.2-GGUF

vantagewithai/LTX2.3-10Eros-1.2-GGUF — v1.2 — Note: files are named 10Eros_v1.210Eros_v1.2-…gguf (upstream double-stamp glitch); we link verbatim.

Quant	Size	Download
![Q3_K_M][badge-Q3_K_M]	10.36 GB	![vantagewithai][gh-vantagewithai]
![Q3_K_S][badge-Q3_K_S]	9.63 GB	![vantagewithai][gh-vantagewithai]
![Q4_0][badge-Q4_0]	12.09 GB	![vantagewithai][gh-vantagewithai]
![Q4_1][badge-Q4_1]	12.95 GB	![vantagewithai][gh-vantagewithai]
![Q4_K_M][badge-Q4_K_M]	13.31 GB	![vantagewithai][gh-vantagewithai]
![Q4_K_S][badge-Q4_K_S]	12.29 GB	![vantagewithai][gh-vantagewithai]
![Q5_0][badge-Q5_0]	14.21 GB	![vantagewithai][gh-vantagewithai]
![Q5_1][badge-Q5_1]	15.07 GB	![vantagewithai][gh-vantagewithai]
![Q5_K_M][badge-Q5_K_M]	15.03 GB	![vantagewithai][gh-vantagewithai]
![Q5_K_S][badge-Q5_K_S]	14.01 GB	![vantagewithai][gh-vantagewithai]
![Q6_K][badge-Q6_K]	16.55 GB	![vantagewithai][gh-vantagewithai]
![Q8_0][badge-Q8_0]	21.19 GB	![vantagewithai][gh-vantagewithai]

vantagewithai/LTX2.3-10Eros-1.3-GGUF

vantagewithai/LTX2.3-10Eros-1.3-GGUF — v1.3

Quant	Size	Download
![Q3_K_M][badge-Q3_K_M]	10.36 GB	![vantagewithai][gh-vantagewithai]
![Q3_K_S][badge-Q3_K_S]	9.63 GB	![vantagewithai][gh-vantagewithai]
![Q4_0][badge-Q4_0]	12.09 GB	![vantagewithai][gh-vantagewithai]
![Q4_1][badge-Q4_1]	12.95 GB	![vantagewithai][gh-vantagewithai]
![Q4_K_M][badge-Q4_K_M]	13.31 GB	![vantagewithai][gh-vantagewithai]
![Q4_K_S][badge-Q4_K_S]	12.29 GB	![vantagewithai][gh-vantagewithai]
![Q5_0][badge-Q5_0]	14.21 GB	![vantagewithai][gh-vantagewithai]
![Q5_1][badge-Q5_1]	15.07 GB	![vantagewithai][gh-vantagewithai]
![Q5_K_M][badge-Q5_K_M]	15.03 GB	![vantagewithai][gh-vantagewithai]
![Q5_K_S][badge-Q5_K_S]	14.01 GB	![vantagewithai][gh-vantagewithai]
![Q6_K][badge-Q6_K]	16.55 GB	![vantagewithai][gh-vantagewithai]
![Q8_0][badge-Q8_0]	21.19 GB	![vantagewithai][gh-vantagewithai]

vantagewithai/LTX2.3-10Eros-1.4-GGUF

vantagewithai/LTX2.3-10Eros-1.4-GGUF — v1.4 (latest)

Quant	Size	Download
![Q3_K_M][badge-Q3_K_M]	10.36 GB	![vantagewithai][gh-vantagewithai]
![Q3_K_S][badge-Q3_K_S]	9.63 GB	![vantagewithai][gh-vantagewithai]
![Q4_0][badge-Q4_0]	12.09 GB	![vantagewithai][gh-vantagewithai]
![Q4_1][badge-Q4_1]	12.95 GB	![vantagewithai][gh-vantagewithai]
![Q4_K_M][badge-Q4_K_M]	13.31 GB	![vantagewithai][gh-vantagewithai]
![Q4_K_S][badge-Q4_K_S]	12.29 GB	![vantagewithai][gh-vantagewithai]
![Q5_0][badge-Q5_0]	14.21 GB	![vantagewithai][gh-vantagewithai]
![Q5_1][badge-Q5_1]	15.07 GB	![vantagewithai][gh-vantagewithai]
![Q5_K_M][badge-Q5_K_M]	15.03 GB	![vantagewithai][gh-vantagewithai]
![Q5_K_S][badge-Q5_K_S]	14.01 GB	![vantagewithai][gh-vantagewithai]
![Q6_K][badge-Q6_K]	16.55 GB	![vantagewithai][gh-vantagewithai]
![Q8_0][badge-Q8_0]	21.19 GB	![vantagewithai][gh-vantagewithai]

vantagewithai/LTX2.3-10Eros-1.5-GGUF

vantagewithai/LTX2.3-10Eros-1.5-GGUF — v1.5 (latest)

Quant	Size	Download
![Q3_K_M][badge-Q3_K_M]	11.13 GB	![vantagewithai][gh-vantagewithai]
![Q3_K_S][badge-Q3_K_S]	10.34 GB	![vantagewithai][gh-vantagewithai]
![Q4_0][badge-Q4_0]	12.98 GB	![vantagewithai][gh-vantagewithai]
![Q4_1][badge-Q4_1]	13.90 GB	![vantagewithai][gh-vantagewithai]
![Q4_K_M][badge-Q4_K_M]	14.30 GB	![vantagewithai][gh-vantagewithai]
![Q4_K_S][badge-Q4_K_S]	13.20 GB	![vantagewithai][gh-vantagewithai]
![Q5_0][badge-Q5_0]	15.26 GB	![vantagewithai][gh-vantagewithai]
![Q5_1][badge-Q5_1]	16.18 GB	![vantagewithai][gh-vantagewithai]
![Q5_K_M][badge-Q5_K_M]	16.14 GB	![vantagewithai][gh-vantagewithai]
![Q5_K_S][badge-Q5_K_S]	15.04 GB	![vantagewithai][gh-vantagewithai]
![Q6_K][badge-Q6_K]	17.77 GB	![vantagewithai][gh-vantagewithai]
![Q8_0][badge-Q8_0]	22.76 GB	![vantagewithai][gh-vantagewithai]

◦ 10Eros Splits

per-version component split

vantagewithai/LTX2.3-10Eros-Split — v1

Component	Precision	Size	Download
Model	![bf16][badge-bf16]	41.03 GB	![vantagewithai][gh-vantagewithai]
Model	![fp8][badge-fp8]	24.45 GB	![vantagewithai][gh-vantagewithai]
VAE	—	1.42 GB	![vantagewithai][gh-vantagewithai]
Audio VAE	—	364.86 MB	![vantagewithai][gh-vantagewithai]
Text encoder	—	2.26 GB	![vantagewithai][gh-vantagewithai]

vantagewithai/LTX2.3-10Eros-1.2-Split — v1.2

Component	Precision	Size	Download
Model	![bf16][badge-bf16]	41.03 GB	![vantagewithai][gh-vantagewithai]
Model	![fp8][badge-fp8]	29.49 GB	![vantagewithai][gh-vantagewithai]
VAE	—	1.42 GB	![vantagewithai][gh-vantagewithai]
Audio VAE	—	364.86 MB	![vantagewithai][gh-vantagewithai]
LoRA (bundled)	—	662.07 MB	![vantagewithai][gh-vantagewithai]

vantagewithai/LTX2.3-10Eros-1.3-Split — v1.3

Component	Precision	Size	Download
Model	![bf16][badge-bf16]	41.03 GB	![vantagewithai][gh-vantagewithai]
Model	![fp8][badge-fp8]	24.45 GB	![vantagewithai][gh-vantagewithai]
VAE	—	1.42 GB	![vantagewithai][gh-vantagewithai]
Audio VAE	—	364.86 MB	![vantagewithai][gh-vantagewithai]
Text encoder	—	2.26 GB	![vantagewithai][gh-vantagewithai]

vantagewithai/LTX2.3-10Eros-1.4-Split — v1.4 (latest)

Component	Precision	Size	Download
Model	![bf16][badge-bf16]	41.03 GB	![vantagewithai][gh-vantagewithai]
Model	![fp8][badge-fp8]	24.45 GB	![vantagewithai][gh-vantagewithai]
VAE	—	1.42 GB	![vantagewithai][gh-vantagewithai]
Audio VAE	—	364.86 MB	![vantagewithai][gh-vantagewithai]
Text encoder	—	2.26 GB	![vantagewithai][gh-vantagewithai]

◦ 10Eros Splits — AX1Y2JP transformer-only fork (alternative split for ComfyUI)

◦ 10Eros Extracted LoRA — maximsobolev275 trained LoRAs

◦ 10Eros distilled-baked collection — ibyteohdear

Massive 10Eros distilled-baked checkpoint collection by ibyteohdear — full LTX distilled checkpoints with the 10Eros style baked in. Spans LTX-2.3 (DISTILLED_BAKED_LTX_SULPHUR_STYLE_IS_10Eros v1–v15, ranks r64 / r128 / r256 / r512 / r768, plus r768_0.85; ~46.1 GB each) and LTX-2.5 (below). Also bundles a JoyAI-Echo_r256 LoRA and reasoning I2V LoRAs (LTX2.3_reasoning_I2V_V3/V4).

· · · · · · · · · · · · · ·

❖ Sulphur-2-base

Repo: SulphurAI/Sulphur-2-base — uncensored video generation model based on LTX 2.3 with built-in prompt enhancer. Merge base for 10Eros. T2V + I2V native.

◦ Main video model

◦ vantagewithai component split — vantagewithai/Sulphur-2-Base-Split

Abiray GGUF quants

◦ Abiray GGUF quants — Abiray/Sulphur-2-base-GGUF

Build	Precision	Size	Download
sulphur_dev	![bf16][badge-bf16]	40.09 GB	![Abiray][gh-Abiray]
sulphur_dev	![Q3_K_M][badge-Q3_K_M]	10.36 GB	![Abiray][gh-Abiray]
sulphur_dev	![Q3_K_S][badge-Q3_K_S]	9.63 GB	![Abiray][gh-Abiray]
sulphur_dev	![Q4_0][badge-Q4_0]	12.09 GB	![Abiray][gh-Abiray]
sulphur_dev	![Q4_K_M][badge-Q4_K_M]	13.31 GB	![Abiray][gh-Abiray]
sulphur_dev	![Q4_K_S][badge-Q4_K_S]	12.29 GB	![Abiray][gh-Abiray]
sulphur_dev	![Q5_0][badge-Q5_0]	14.21 GB	![Abiray][gh-Abiray]
sulphur_dev	![Q5_K_M][badge-Q5_K_M]	15.04 GB	![Abiray][gh-Abiray]
sulphur_dev	![Q5_K_S][badge-Q5_K_S]	14.01 GB	![Abiray][gh-Abiray]
sulphur_dev	![Q6_K][badge-Q6_K]	16.55 GB	![Abiray][gh-Abiray]
sulphur_dev	![Q8_0][badge-Q8_0]	21.19 GB	![Abiray][gh-Abiray]

◦ Sulphur LoRAs

◦ Prompt Enhancer

· · · · · · · · · · · · · ·

❖ JoyAI-Echo Surgical

Surgical finetune based on jdopensource/JoyAI-Echo by joeygambino. Combined "echoVid + ltxAud" surgical variant — jointly fine-tuned for both video generation and audio on top of LTX-2.3. A LoRA extracted from JoyAI-Echo (TenStrip's LTX2.3_JoyAI_Lora_Extracted) is listed separately under ### ▣ Special.

◦ JoyAI-Echo Surgical — GGUF (low-VRAM quants)

joeygambino/joyai-echo-ltx23-echoVid-ltxAud-surgical-gguf

joeygambino/joyai-echo-ltx23-echoVid-ltxAud-surgical-gguf — Surgical DiT GGUF quants by joeygambino.

Ver	Build	Name	Precision	Size	Download
2.3	GGUF	echoVid-ltxAud surgical	![Q5_0][badge-Q5_0]	15.54 GB	![joeygambino][gh-joeygambino]
2.3	GGUF	echoVid-ltxAud surgical	![Q8_0][badge-Q8_0]	23.13 GB	![joeygambino][gh-joeygambino]

· · · · · · · · · · · · · ·

❖ JoyAI-Echo (LTX-2.5)

Surgical merge of jdopensource/JoyAI-Echo into the LTX-2.5 dev transformer by joeygambino — JoyAI-Echo's video attention / feed-forward delta transplanted in, with nothing distilled baked on top. Three builds: dev (bring-your-own distill LoRA), comfy-native (few-step, distill baked at 0.5 — RTX 50), and GGUF (few-step — RTX 30/40). Two doses per build: 070T30 (0.7× delta / 0.3× modulation) and 100T50 (1.0× / 0.5×). Workflows: ComfyUI-JoyLTX25.

Z-Image surface-graft variant (× Z-Image) — same echoVid 070T30 v2 engine with Z-Image's spatial attention profile grafted in as per-block q_norm rescaling (dose 0.5, no retraining, no Z-Image weights at inference). Targets surface/texture rendering: fine detail on foliage, straw, gravel, fabric and skin. Drop-in replacement for any stock v2 workflow — same loaders, settings and seeds.

◦ JoyAI-Echo × Z-Image — GGUF (RTX 30/40; K-quants run 4–8× faster than emulated 4-bit there)

joeygambino/joyai-echo-ltx25-x-Z-Image-gguf

joeygambino/joyai-echo-ltx25-x-Z-Image-gguf — Z-Image-grafted echoVid 070T30 v2 GGUF quants by joeygambino (Q4_K_M/Q4_K_S are the RTX 30/40 sweet spot).

Ver	Build	Name	Precision	Size	Download
2.5	GGUF	echoVid 070T30 × Z-Image zgraft05	![Q2_K][badge-Q2_K]	7.91 GB	![joeygambino][gh-joeygambino]
2.5	GGUF	echoVid 070T30 × Z-Image zgraft05	![Q3_K_M][badge-Q3_K_M]	10.60 GB	![joeygambino][gh-joeygambino]
2.5	GGUF	echoVid 070T30 × Z-Image zgraft05	![Q4_K_M][badge-Q4_K_M]	14.17 GB	![joeygambino][gh-joeygambino]
2.5	GGUF	echoVid 070T30 × Z-Image zgraft05	![Q4_K_S][badge-Q4_K_S]	12.93 GB	![joeygambino][gh-joeygambino]
2.5	GGUF	echoVid 070T30 × Z-Image zgraft05	![Q5_K_M][badge-Q5_K_M]	15.90 GB	![joeygambino][gh-joeygambino]
2.5	GGUF	echoVid 070T30 × Z-Image zgraft05	![Q6_K][badge-Q6_K]	17.75 GB	![joeygambino][gh-joeygambino]
2.5	GGUF	echoVid 070T30 × Z-Image zgraft05	![Q8_0][badge-Q8_0]	22.73 GB	![joeygambino][gh-joeygambino]

◦ JoyAI-Echo (LTX-2.5) — GGUF (low-VRAM quants)

joeygambino/joyai-echo-ltx25-echoVid-gguf

joeygambino/joyai-echo-ltx25-echoVid-gguf — echoVid GGUF quants by joeygambino (few-step, distill baked at 0.5; RTX 30/40).

Ver	Build	Name	Precision	Size	Download
2.5	GGUF	echoVid 070T30	![Q2_K][badge-Q2_K]	7.91 GB	![joeygambino][gh-joeygambino]
2.5	GGUF	echoVid 070T30	![Q3_K_M][badge-Q3_K_M]	10.60 GB	![joeygambino][gh-joeygambino]
2.5	GGUF	echoVid 070T30	![Q4_K_M][badge-Q4_K_M]	14.17 GB	![joeygambino][gh-joeygambino]
2.5	GGUF	echoVid 070T30	![Q4_K_S][badge-Q4_K_S]	12.93 GB	![joeygambino][gh-joeygambino]
2.5	GGUF	echoVid 070T30	![Q5_K_M][badge-Q5_K_M]	15.90 GB	![joeygambino][gh-joeygambino]
2.5	GGUF	echoVid 070T30	![Q6_K][badge-Q6_K]	17.75 GB	![joeygambino][gh-joeygambino]
2.5	GGUF	echoVid 070T30	![Q8_0][badge-Q8_0]	22.73 GB	![joeygambino][gh-joeygambino]
2.5	GGUF	echoVid 100T50	![Q2_K][badge-Q2_K]	7.91 GB	![joeygambino][gh-joeygambino]
2.5	GGUF	echoVid 100T50	![Q3_K_M][badge-Q3_K_M]	10.60 GB	![joeygambino][gh-joeygambino]
2.5	GGUF	echoVid 100T50	![Q4_K_M][badge-Q4_K_M]	14.17 GB	![joeygambino][gh-joeygambino]
2.5	GGUF	echoVid 100T50	![Q4_K_S][badge-Q4_K_S]	12.93 GB	![joeygambino][gh-joeygambino]
2.5	GGUF	echoVid 100T50	![Q5_K_M][badge-Q5_K_M]	15.90 GB	![joeygambino][gh-joeygambino]
2.5	GGUF	echoVid 100T50	![Q6_K][badge-Q6_K]	17.75 GB	![joeygambino][gh-joeygambino]
2.5	GGUF	echoVid 100T50	![Q8_0][badge-Q8_0]	22.73 GB	![joeygambino][gh-joeygambino]

· · · · · · · · · · · · · ·

❖ PinkCherry NSFW

Repo: SexGod1979/PinkCherry_NSFW_LTX23 — uncensored NSFW LTX-2.3 finetune family (NSFW content only — do not use for clean content). Pairs with the official LTX-2.3 distilled LoRA 384.

◦ PinkCherry GGUF — low-VRAM quants by SexGod1979

v1.7-alpha / v1.8 GGUF

Quant	Build	Size	Download
![Q5_K_M][badge-Q5_K_M]	v1.7-alpha	15.93 GB	![PinkCherry][gh-SexGod1979]
![Q6_K][badge-Q6_K]	v1.7-alpha	17.77 GB	![PinkCherry][gh-SexGod1979]
![Q5_K_M][badge-Q5_K_M]	v1.8	15.93 GB	![PinkCherry][gh-SexGod1979]
![Q8_0][badge-Q8_0]	v1.8	22.76 GB	![PinkCherry][gh-SexGod1979]

❖ Elastic

Elastic is a TensorRT-engine distribution of a LoRA-integrated distilled FP8 T2V variant of LTX-2.3, packaged by TheStageAI as .qlip shard files for H100 GPUs.

❖ ChrisColeTech Uncensored Turbo

Pre-merged LTX-2.3 Uncensored Turbo v1.4 DiT by ChrisColeTech with three fine-tunes baked into the weights: 10Eros NSFW LoRA (1.0), DMD distilled LoRA (1.0, 4-step capable — 8 steps recommended), and the official LTXV ICLoRA Detailer (0.6). Modes: T2AV / I2AV / V2V / A2V / REF2VA; example workflows bundled in the repo.

◦ Component splits (uncensored v1.4 text encoder / projections / VAEs, plus the older v1.0 uncensored build and stock LTX-2.3 distilled fp8) live in the same repo under split/ — see the repo tree for the full list.

v1.0 builds (older, also in this repo)

Ver	Build	Precision	Size	Download
2.3	v1.0 fp8	![fp8][badge-fp8]	29.16 GB	![ChrisColeTech][gh-ChrisColeTech]
2.3	v1.0 int8	![int8tensormixed][badge-int8tensormixed]	29.16 GB	![ChrisColeTech][gh-ChrisColeTech]
2.3	v1.0 GGUF	![Q4_K_M][badge-Q4_K_M]	14.30 GB	![ChrisColeTech][gh-ChrisColeTech]
2.3	v1.0 GGUF	![Q6_K][badge-Q6_K]	17.77 GB	![ChrisColeTech][gh-ChrisColeTech]
2.3	v1.0 GGUF	![Q8_0][badge-Q8_0]	22.76 GB	![ChrisColeTech][gh-ChrisColeTech]

· · · · · · · · · · · · · ·

❖ REDGraft (NSFW)

Uncensored NSFW LTX-2.5 checkpoint by EllaPriest45 ("REDGraft"), shipped as a single INT8 full checkpoint together with a bundled two-stage i2V workflow JSON (ManualSigmas ×2 + LoRA loader).

◦ Bundled workflow: REDGraft (NSFW) INT8 - LTX2.5.json.

· · · · · · · · · · · · · ·

❖ SpatialAV2AV (BingoG)

Publicly-released audio→audio-video training checkpoints from BingoG/LTX-2-SpatialAV2AV-Checkpoints for spatial-audio conditioned video generation. Two curriculum layouts (E4 Core Dual + Dynamic; E6 reserved for Full) at 480p cap, 113 frames at 25 fps.

Note: these are intermediate training checkpoints, not inference-ready models — useful for fine-tuning experiments and reproducibility only.

· · · · · · · · · · · · · ·

❖ One-Step Refiner (Owen777)

One-step LTX-2.5 video refiner by Owen777 — a DMD/GAN-style one-step refinement model (EMA step 835) that sharpens/refines generated video in a single pass. Access is gated — request access on the repo before downloading.

◦ Reinforcement-learning LoRA also in repo: rl_lora/step_000400.pt (~0.81 GB).

❖ SoL-Refiner — one-step 1080p/2K upscaler (szwagros, int8 ConvRot)

Generic one-step refiner from NVlabs' SoL-Refiner project (SANA / SANA-Video): a cheap low-res draft (SANA-Video, WAN, MiniMax-H3, …) is encoded, 2x latent-upscaled with AdaIN, re-noised and denoised in a single transformer forward, turning the draft into 1080p/2K output. Repackaged by szwagros from the Efficient-Large-Model originals into the image-server ltx_core layout (diffusion_models/ + text_encoders/ + vae/ + latent_upscale_models/) — the transformer and text encoder are int8 ConvRot and expect the image_server_kernels.int8_linear backend, so these are not drop-in ComfyUI checkpoints.

LTX-2.3 One-Step — szwagros/SoL-Refiner-LTX-2.3-One-Step-int8-convrot · 41.93 GB total · re-noised to sigma 0.725

⚠️ Always condition with frame_rate=16, whatever the input fps (encode the output at the real fps) — the model was trained on 16 fps drafts and a 24 fps value mis-scales the temporal RoPE and ghosts moving objects. Uses the v1.1 x2 upsampler, not v1.0.

LTX-2.5 for MiniMax-H3 — szwagros/SoL-Refiner-LTX-2.5-H3-int8-convrot · 41.35 GB total · re-noised to sigma 0.909375

◦ Conditioning frame_rate = the input fps (H3 drafts are 24 fps). One step, no CFG. Video output only — no audio. The text encoder is the refiner's shipped Gemma 4, i.e. the pre-2026-08-17 Lightricks encoder rather than the current one.

◦ Both are finetunes of LTX-2.x, so the LTX-2.x Community License (Lightricks) applies — check it before commercial use. Source repos: 2.3 One-Step · 2.5 for MiniMax-H3.

· · · · · · · · · · · · · ·

❖ SolarWM (World Model)

Research LTX-2.5 world model by junchaoh-cs (arXiv:2609.02886) — a long-horizon, camera-controllable video world model finetuned from LTX-2.5 22B. The repo re-ships the LTX-2.5 22B base (dev transformer + gemma4-12b text encoder + VAE) plus a finetuned stage, SolarWM-ltx-22B-bid-stage0p5-153f (EMA weights, ema/model.safetensors). Access is gated — request access before downloading; exact artifact formats are unconfirmed (gated).

◦ Base LTX-2.5 22B (dev transformer + gemma4-12b encoder + VAE) also in repo. Paper: arXiv:2609.02886.

══════════════════════════════════

▣ GGUF Quantized Models

These models are optimized for lower memory usage. Note that in ComfyUI, these are typically loaded as transformer-only models.

QuantStack

QuantStack LTX-2.3

Model	Quant	Size	Download
ltx-2.3-22b	![Q2_K][badge-Q2_K]	12.4 GB	dev ┊ distilled ┊ distilled-1.1
ltx-2.3-22b	![Q3_K_M][badge-Q3_K_M]	14.7 GB	dev ┊ distilled ┊ distilled-1.1
ltx-2.3-22b	![Q3_K_S][badge-Q3_K_S]	14 GB	dev ┊ distilled ┊ distilled-1.1
ltx-2.3-22b	![Q4_K_M][badge-Q4_K_M]	17.8 GB	dev ┊ distilled ┊ distilled-1.1
ltx-2.3-22b	![Q4_K_S][badge-Q4_K_S]	16.7 GB	dev ┊ distilled ┊ distilled-1.1
ltx-2.3-22b	![Q5_K_M][badge-Q5_K_M]	19.4 GB	dev ┊ distilled ┊ distilled-1.1
ltx-2.3-22b	![Q5_K_S][badge-Q5_K_S]	18.5 GB	dev ┊ distilled ┊ distilled-1.1
ltx-2.3-22b	![Q6_K][badge-Q6_K]	21 GB	dev ┊ distilled ┊ distilled-1.1
ltx-2.3-22b	![Q8_0][badge-Q8_0]	25.5 GB	dev ┊ distilled ┊ distilled-1.1

QuantStack LTX-2

Model	Quant	Size	Download
LTX-2-dev	![Q2_K][badge-Q2_K]	8.03 GB	![][gh-QuantStack]
LTX-2-dev	![Q3_K_M][badge-Q3_K_M]	10.3 GB	![][gh-QuantStack]
LTX-2-dev	![Q3_K_S][badge-Q3_K_S]	9.57 GB	![][gh-QuantStack]
LTX-2-dev	![Q4_K_M][badge-Q4_K_M]	13.4 GB	![][gh-QuantStack]
LTX-2-dev	![Q4_K_S][badge-Q4_K_S]	12.3 GB	![][gh-QuantStack]
LTX-2-dev	![Q5_K_M][badge-Q5_K_M]	15 GB	![][gh-QuantStack]
LTX-2-dev	![Q5_K_S][badge-Q5_K_S]	14.2 GB	![][gh-QuantStack]
LTX-2-dev	![Q6_K][badge-Q6_K]	16.6 GB	![][gh-QuantStack]
LTX-2-dev	![Q8_0][badge-Q8_0]	21.1 GB	![][gh-QuantStack]

Unsloth

Unsloth LTX-2.3 GGUF

Model	Quant	Size	Download
ltx-2.3-22b	![BF16][badge-BF16]	42 GB	dev ┊ distilled
ltx-2.3-22b	![F16][badge-F16]	42 GB	dev ┊ distilled
ltx-2.3-22b	![Q2_K][badge-Q2_K]	8.28 GB	dev ┊ distilled
ltx-2.3-22b	![Q3_K_M][badge-Q3_K_M]	10.8 GB	dev ┊ distilled
ltx-2.3-22b	![Q3_K_S][badge-Q3_K_S]	9.95 GB	dev ┊ distilled
ltx-2.3-22b	![Q4_0][badge-Q4_0]	12.7 GB	dev ┊ distilled
ltx-2.3-22b	![Q4_1][badge-Q4_1]	13.8 GB	dev ┊ distilled
ltx-2.3-22b	![Q4_K_M][badge-Q4_K_M]	14.3 GB	dev ┊ distilled
ltx-2.3-22b	![Q4_K_S][badge-Q4_K_S]	13.1 GB	dev ┊ distilled
ltx-2.3-22b	![Q5_0][badge-Q5_0]	15.3 GB	dev ┊ distilled
ltx-2.3-22b	![Q5_1][badge-Q5_1]	16.3 GB	dev ┊ distilled
ltx-2.3-22b	![Q5_K_M][badge-Q5_K_M]	16.1 GB	dev ┊ distilled
ltx-2.3-22b	![Q5_K_S][badge-Q5_K_S]	15.2 GB	dev ┊ distilled
ltx-2.3-22b	![Q6_K][badge-Q6_K]	17.8 GB	dev ┊ distilled
ltx-2.3-22b	![Q8_0][badge-Q8_0]	22.8 GB	dev ┊ distilled
ltx-2.3-22b	![UD-Q2_K][badge-UD-Q2_K]	9.5 GB	dev ┊ distilled
ltx-2.3-22b	![UD-Q3_K_M][badge-UD-Q3_K_M]	13.5 GB	dev ┊ distilled
ltx-2.3-22b		11.4 GB	dev ┊ distilled
ltx-2.3-22b	![UD-Q4_K_M][badge-UD-Q4_K_M]	16.5 GB	dev ┊ distilled
ltx-2.3-22b	![UD-Q4_K_S][badge-UD-Q4_K_S]	14.2 GB	dev ┊ distilled
ltx-2.3-22b	![UD-Q5_K_M][badge-UD-Q5_K_M]	18.3 GB	dev ┊ distilled
ltx-2.3-22b		16.3 GB	dev ┊ distilled

Unsloth LTX-2.3 GGUF - Distilled 1.1

Model	Quant	Size	Download
ltx-2.3-22b	![BF16][badge-BF16]	42 GB	distilled-1.1
ltx-2.3-22b	![F16][badge-F16]	42 GB	distilled-1.1
ltx-2.3-22b	![Q2_K][badge-Q2_K]	7.94 GB	distilled-1.1
ltx-2.3-22b	![Q3_K_M][badge-Q3_K_M]	10.6 GB	distilled-1.1
ltx-2.3-22b	![Q3_K_S][badge-Q3_K_S]	9.74 GB	distilled-1.1
ltx-2.3-22b	![Q4_K_M][badge-Q4_K_M]	14.2 GB	distilled-1.1
ltx-2.3-22b	![Q4_K_S][badge-Q4_K_S]	13 GB	distilled-1.1
ltx-2.3-22b	![Q5_K_M][badge-Q5_K_M]	15.9 GB	distilled-1.1
ltx-2.3-22b	![Q5_K_S][badge-Q5_K_S]	15 GB	distilled-1.1
ltx-2.3-22b	![Q6_K][badge-Q6_K]	17.8 GB	distilled-1.1
ltx-2.3-22b	![Q8_0][badge-Q8_0]	22.8 GB	distilled-1.1
ltx-2.3-22b	![UD-Q2_K][badge-UD-Q2_K]	10.9 GB	distilled-1.1
ltx-2.3-22b	![UD-Q3_K_M][badge-UD-Q3_K_M]	13.4 GB	distilled-1.1
ltx-2.3-22b	![UD-Q4_K_M][badge-UD-Q4_K_M]	16.4 GB	distilled-1.1
ltx-2.3-22b	![UD-Q4_K_S][badge-UD-Q4_K_S]	14.1 GB	distilled-1.1
ltx-2.3-22b	![UD-Q5_K_M][badge-UD-Q5_K_M]	18.2 GB	distilled-1.1

Unsloth LTX-2 GGUF

Model	Quant	Size	Download
ltx-2-19b-dev	![BF16][badge-BF16]	37.8 GB	![][gh-Unsloth]
ltx-2-19b-dev	![F16][badge-F16]	37.8 GB	![][gh-Unsloth]
ltx-2-19b-dev		10.1 GB	![][gh-Unsloth]
ltx-2-19b-dev		11.6 GB	![][gh-Unsloth]
ltx-2-19b-dev	![Q2_K][badge-Q2_K]	8.1 GB	![][gh-Unsloth]
ltx-2-19b-dev		10.7 GB	![][gh-Unsloth]
ltx-2-19b-dev	![Q3_K_M][badge-Q3_K_M]	10.1 GB	![][gh-Unsloth]
ltx-2-19b-dev	![Q3_K_S][badge-Q3_K_S]	9.47 GB	![][gh-Unsloth]
ltx-2-19b-dev	![Q4_0][badge-Q4_0]	11.3 GB	![][gh-Unsloth]
ltx-2-19b-dev	![Q4_1][badge-Q4_1]	12.3 GB	![][gh-Unsloth]
ltx-2-19b-dev	![Q4_K_M][badge-Q4_K_M]	12.8 GB	![][gh-Unsloth]
ltx-2-19b-dev	![Q4_K_S][badge-Q4_K_S]	11.9 GB	![][gh-Unsloth]
ltx-2-19b-dev	![Q5_0][badge-Q5_0]	13.7 GB	![][gh-Unsloth]
ltx-2-19b-dev	![Q5_1][badge-Q5_1]	14.6 GB	![][gh-Unsloth]
ltx-2-19b-dev	![Q5_K_M][badge-Q5_K_M]	14.3 GB	![][gh-Unsloth]
ltx-2-19b-dev	![Q5_K_S][badge-Q5_K_S]	13.6 GB	![][gh-Unsloth]
ltx-2-19b-dev	![Q6_K][badge-Q6_K]	16 GB	![][gh-Unsloth]
ltx-2-19b-dev	![Q8_0][badge-Q8_0]	20.4 GB	![][gh-Unsloth]

Vantage

Vantage AI GGUFs

Model	Quant	Size	Download
ltx-2-19b-dev	![Q3_K_M][badge-Q3_K_M]	9.96 GB	![][gh-vantagewithai]
ltx-2-19b-dev	![Q3_K_S][badge-Q3_K_S]	9.28 GB	![][gh-vantagewithai]
ltx-2-19b-dev	![Q4_0][badge-Q4_0]	11.6 GB	![][gh-vantagewithai]
ltx-2-19b-dev	![Q4_1][badge-Q4_1]	12.4 GB	![][gh-vantagewithai]
ltx-2-19b-dev	![Q4_K_M][badge-Q4_K_M]	12.8 GB	![][gh-vantagewithai]
ltx-2-19b-dev	![Q4_K_S][badge-Q4_K_S]	11.8 GB	![][gh-vantagewithai]
ltx-2-19b-dev	![Q5_0][badge-Q5_0]	13.6 GB	![][gh-vantagewithai]
ltx-2-19b-dev	![Q5_1][badge-Q5_1]	14.5 GB	![][gh-vantagewithai]
ltx-2-19b-dev	![Q5_K_M][badge-Q5_K_M]	14.4 GB	![][gh-vantagewithai]
ltx-2-19b-dev	![Q5_K_S][badge-Q5_K_S]	13.5 GB	![][gh-vantagewithai]
ltx-2-19b-dev	![Q6_K][badge-Q6_K]	15.9 GB	![][gh-vantagewithai]
ltx-2-19b-dev	![Q8_0][badge-Q8_0]	20.4 GB	![][gh-vantagewithai]
ltx-2-19b-distilled	![Q3_K_M][badge-Q3_K_M]	9.96 GB	![][gh-vantagewithai]
ltx-2-19b-distilled	![Q3_K_S][badge-Q3_K_S]	9.28 GB	![][gh-vantagewithai]
ltx-2-19b-distilled	![Q4_0][badge-Q4_0]	11.6 GB	![][gh-vantagewithai]
ltx-2-19b-distilled	![Q4_1][badge-Q4_1]	12.4 GB	![][gh-vantagewithai]
ltx-2-19b-distilled	![Q4_K_M][badge-Q4_K_M]	12.8 GB	![][gh-vantagewithai]
ltx-2-19b-distilled	![Q4_K_S][badge-Q4_K_S]	11.8 GB	![][gh-vantagewithai]
ltx-2-19b-distilled	![Q5_0][badge-Q5_0]	13.6 GB	![][gh-vantagewithai]
ltx-2-19b-distilled	![Q5_1][badge-Q5_1]	14.5 GB	![][gh-vantagewithai]
ltx-2-19b-distilled	![Q5_K_M][badge-Q5_K_M]	14.4 GB	![][gh-vantagewithai]
ltx-2-19b-distilled	![Q5_K_S][badge-Q5_K_S]	13.5 GB	![][gh-vantagewithai]
ltx-2-19b-distilled	![Q6_K][badge-Q6_K]	15.9 GB	![][gh-vantagewithai]
ltx-2-19b-distilled	![Q8_0][badge-Q8_0]	20.4 GB	![][gh-vantagewithai]

Abiray LTX-2.5 Distilled GGUF

Abiray/LTX-2.5-Distilled-GGUF

Model	Quant	Size	Download
ltx-2.5-22b-distilled	![Q3_K_M][badge-Q3_K_M]	12.92 GB	![][gh-Abiray]
ltx-2.5-22b-distilled	![Q3_K_S][badge-Q3_K_S]	12.65 GB	![][gh-Abiray]
ltx-2.5-22b-distilled	![Q4_K_M][badge-Q4_K_M]	15.69 GB	![][gh-Abiray]
ltx-2.5-22b-distilled	![Q4_K_S][badge-Q4_K_S]	15.33 GB	![][gh-Abiray]
ltx-2.5-22b-distilled	![Q5_K_M][badge-Q5_K_M]	18.12 GB	![][gh-Abiray]
ltx-2.5-22b-distilled	![Q6_K][badge-Q6_K]	18.62 GB	![][gh-Abiray]
ltx-2.5-22b-distilled	![Q8_0][badge-Q8_0]	23.60 GB	![][gh-Abiray]

Abiray LTX-2.5 GGUF

Abiray/LTX-2.5-GGUF

Model	Quant	Size	Download
ltx-2.5-22b	![Q3_K_M][badge-Q3_K_M]	9.89 GB	![][gh-Abiray]
ltx-2.5-22b	![Q3_K_S][badge-Q3_K_S]	9.07 GB	![][gh-Abiray]
ltx-2.5-22b	![Q4_K_M][badge-Q4_K_M]	13.21 GB	![][gh-Abiray]
ltx-2.5-22b	![Q4_K_S][badge-Q4_K_S]	12.07 GB	![][gh-Abiray]
ltx-2.5-22b	![Q5_K_M][badge-Q5_K_M]	14.83 GB	![][gh-Abiray]
ltx-2.5-22b	![Q5_K_S][badge-Q5_K_S]	14.01 GB	![][gh-Abiray]
ltx-2.5-22b	![Q6_K][badge-Q6_K]	16.55 GB	![][gh-Abiray]
ltx-2.5-22b	![Q8_0][badge-Q8_0]	21.19 GB	![][gh-Abiray]

realrebelai LTX-2.5 GGUFs

realrebelai/LTX-2.5_GGUFs

Model	Quant	Size	Download
ltx-2.5-22b-distilled	![Q2_K][badge-Q2_K]	8.23 GB	![][gh-realrebelai]
ltx-2.5-22b-distilled	![Q3_K_M][badge-Q3_K_M]	10.73 GB	![][gh-realrebelai]
ltx-2.5-22b-distilled	![Q4_K_M][badge-Q4_K_M]	14.05 GB	![][gh-realrebelai]
ltx-2.5-22b-distilled	![Q4_K_S][badge-Q4_K_S]	12.90 GB	![][gh-realrebelai]
ltx-2.5-22b-distilled	![Q5_K_M][badge-Q5_K_M]	15.66 GB	![][gh-realrebelai]
ltx-2.5-22b-distilled	![Q6_K][badge-Q6_K]	17.38 GB	![][gh-realrebelai]
ltx-2.5-22b-distilled	![Q8_0][badge-Q8_0]	22.01 GB	![][gh-realrebelai]

vantagewithai LTX-2.5 GGUF

vantagewithai/LTX-2.5-GGUF

Model	Quant	Size	Download
ltx-2.5-22b-dev	![Q2_K][badge-Q2_K]	12.13 GB	![][gh-vantagewithai]
ltx-2.5-22b-dev	![Q3_K_M][badge-Q3_K_M]	12.92 GB	![][gh-vantagewithai]
ltx-2.5-22b-dev	![Q3_K_S][badge-Q3_K_S]	12.65 GB	![][gh-vantagewithai]
ltx-2.5-22b-dev	![Q4_0][badge-Q4_0]	15.24 GB	![][gh-vantagewithai]
ltx-2.5-22b-dev	![Q4_1][badge-Q4_1]	15.53 GB	![][gh-vantagewithai]
ltx-2.5-22b-dev	![Q4_K_M][badge-Q4_K_M]	15.69 GB	![][gh-vantagewithai]
ltx-2.5-22b-dev	![Q4_K_S][badge-Q4_K_S]	15.33 GB	![][gh-vantagewithai]
ltx-2.5-22b-dev	![Q5_0][badge-Q5_0]	15.98 GB	![][gh-vantagewithai]
ltx-2.5-22b-dev	![Q5_1][badge-Q5_1]	16.26 GB	![][gh-vantagewithai]
ltx-2.5-22b-dev	![Q5_K_M][badge-Q5_K_M]	18.12 GB	![][gh-vantagewithai]
ltx-2.5-22b-dev	![Q5_K_S][badge-Q5_K_S]	15.89 GB	![][gh-vantagewithai]
ltx-2.5-22b-dev	![Q6_K][badge-Q6_K]	18.62 GB	![][gh-vantagewithai]
ltx-2.5-22b-dev	![Q8_0][badge-Q8_0]	23.60 GB	![][gh-vantagewithai]
ltx-2.5-22b-distilled	![Q2_K][badge-Q2_K]	12.13 GB	![][gh-vantagewithai]
ltx-2.5-22b-distilled	![Q3_K_M][badge-Q3_K_M]	12.92 GB	![][gh-vantagewithai]
ltx-2.5-22b-distilled	![Q3_K_S][badge-Q3_K_S]	12.65 GB	![][gh-vantagewithai]
ltx-2.5-22b-distilled	![Q4_0][badge-Q4_0]	15.24 GB	![][gh-vantagewithai]
ltx-2.5-22b-distilled	![Q4_1][badge-Q4_1]	15.53 GB	![][gh-vantagewithai]
ltx-2.5-22b-distilled	![Q4_K_M][badge-Q4_K_M]	15.69 GB	![][gh-vantagewithai]
ltx-2.5-22b-distilled	![Q4_K_S][badge-Q4_K_S]	15.33 GB	![][gh-vantagewithai]
ltx-2.5-22b-distilled	![Q5_0][badge-Q5_0]	15.98 GB	![][gh-vantagewithai]
ltx-2.5-22b-distilled	![Q5_1][badge-Q5_1]	16.26 GB	![][gh-vantagewithai]
ltx-2.5-22b-distilled	![Q5_K_M][badge-Q5_K_M]	18.12 GB	![][gh-vantagewithai]
ltx-2.5-22b-distilled	![Q5_K_S][badge-Q5_K_S]	15.89 GB	![][gh-vantagewithai]
ltx-2.5-22b-distilled	![Q6_K][badge-Q6_K]	18.62 GB	![][gh-vantagewithai]
ltx-2.5-22b-distilled	![Q8_0][badge-Q8_0]	23.60 GB	![][gh-vantagewithai]

Special Quantization: PolarQuant Q5

LTX-2.3 (22B) — PolarQuant Q5 is a bit-packed quantization method using Hadamard-Rotated Lloyd-Max Quantization. It achieves optimal Gaussian weight quantization via Hadamard rotation, delivering near-lossless quality with significant size reduction.

Specification

Specification	Value
Parameters	22B
Transformer Blocks	48
Hidden Dimension	4096
Layers Quantized	1,347 (of 5,947 total tensors)

Compression Statistics:

Component	Original Size	PQ5 Packed	Reduction
Transformer (1,347 layers)	37 GB	4.6 GB	-88%
VAE + Skip (4,600 layers)	9.1 GB	9.1 GB	BF16 kept
Upscalers	1.3 GB	1.3 GB	BF16 kept
Total	46.2 GB	15 GB	-68%

Quality Metrics:

• Cosine Similarity: 0.9986 (near-lossless)
• Download Size: 15 GB
• Beats torchao INT4 on perplexity (PPL)

Hardware Requirements:

GPU	VRAM	Status
A100 (80 GB)	80 GB	Full speed
A100 (40 GB)	40 GB	Recommended
RTX 4090 (24 GB)	24 GB	With offloading

Key Features:

• Mixed precision approach: transformer heavily quantized (-88%) while VAE remains BF16
• 5-bit bit-packed representation (Q5)
• 50-65% smaller than original with zero quality loss
• One-command setup with easy generation wrapper

Installation: pip install safetensors huggingface_hub scipy ArXiv Reference: 2603.29078

◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆

▓ Text Encoders

LTX-2/2.3 require Gemma-3-12b variants with text projection layers. LTX-2.5 ships with a Gemma-4-12B text encoder — see the ▣ Gemma-4-12b section below.

▣ Comfy-Org Optimized Encoders

Official and optimized versions for ComfyUI.

• gemma_3_12B_it_fpmixed: Experimental quant. Should be better than the fp8 scaled
• gemma_3_12B_it_fp4_mixed: 90% fp4 layers Note: mxfp8mixed quantization requires a custom fork of ComfyUI-Kitchen with mxfp8 support. Standard ComfyUI setups don't.

· · · · · · · · · · · · · ·

▣ Gemma-3-12b Abliterated

Why Choose Abliterated Encoders?

Standard Gemma models often incorporate safety alignment that "sanitizes" or weakens specific concepts within prompt embeddings. Even when the model doesn't explicitly refuse a request, this internal filtering can dilute creative intent. For LTX-2 video generation, using a standard encoder often results in:

• Reduced Prompt Adherence: Key stylistic or descriptive terms may be ignored or weakened.
• Visual Softening: Visual intensity and fine details are often "muted" to fit generic safety profiles.
• Concept Dilution: Complex or niche creative requests are subtly altered, leading to less faithful representations of your vision.

Abliteration bypasses these restrictive alignment layers, allowing the encoder to translate your prompts into embeddings with maximum fidelity. This ensures LTX-2 receives the most accurate and un-filtered instructions possible.

Gemma-3-12b-Abliterated (FusionCow)

Fixed versions of the abliterated Gemma-3-12b-it model by FusionCow, modified specifically for compatibility with LTX-2. The original model

Model	Precision	Size	Download
Gemma ablit fixed	![bf16][badge-bf16]	23.5 GB	![][gh-FusionCow]
Gemma ablit fixed	![fp8][badge-fp8]	13.8 GB	![][gh-FusionCow]

Sikaworld1990 Gemma-3-12b Abliterated

NVFP4 quantization variants by Sikaworld1990 optimized for Blackwell GPUs.

Model	Precision	Size	Download
Gemma-3-12b QAT Abliterated FP4		12.1 GB	![][gh-Sikaworld1990]
Gemma-3-12b QAT Abliterated FP4		8.91 GB	![][gh-Sikaworld1990]
Gemma-3-12b HereticX Abliterated	![bf16][badge-bf16]	15 GB	![][gh-Sikaworld1990]
Gemma-3-12b High-Fidelity Abliterated	![bf16][badge-bf16]	14.1 GB	![][gh-Sikaworld1990]

• FP4-HF: High-fidelity mixed precision calibration
• FP4-Pure: Pure FP4 quantization for maximum compression
• HereticX: Uncensored variant with maximum prompt fidelity
• High-Fidelity: Optimized for quality with better detail preservation

· · · · · · · · · · · · · ·

▣ Gemma-3-12b IT Heretic

Models by DreamFast. "Heretic" lineage bypasses alignment/restriction layers in the text encoder so LTX-2/2.3 receives the most faithful prompt embeddings. Two upstream versions (v1, v2) plus an AX1Y2JP ultra-uncensored fork and a 3rd-party mradermacher imatrix GGUF re-quant set.

Heretic v1 — DreamFast (bf16 + fp8 + 8 GGUFs)

Safetensors

Model	Precision	Size	Download
Gemma_3_12B_it Heretic	![bf16][badge-bf16]	23.5 GB	![][gh-DreamFast]
Gemma_3_12B_it Heretic	![fp8][badge-fp8]	12.8 GB	![][gh-DreamFast]

GGUF

Quant	Size	Download
![F16][badge-F16]	22 GB	![][gh-DreamFast]
![Q8_0][badge-Q8_0]	12 GB	![][gh-DreamFast]
![Q6_K][badge-Q6_K]	9.0 GB	![][gh-DreamFast]
![Q5_K_M][badge-Q5_K_M]	7.9 GB	![][gh-DreamFast]
![Q5_K_S][badge-Q5_K_S]	7.7 GB	![][gh-DreamFast]
![Q4_K_M][badge-Q4_K_M]	6.8 GB	![][gh-DreamFast]
![Q4_K_S][badge-Q4_K_S]	6.5 GB	![][gh-DreamFast]
![Q3_K_M][badge-Q3_K_M]	5.6 GB	![][gh-DreamFast]

Heretic v2 — DreamFast (5 safetensors + 8 GGUFs)

Safetensors

Model	Precision	Size	Download
gemma-3-12b-it-heretic-v2	![bf16][badge-bf16]	23.25 GB	![][gh-DreamFast]
gemma-3-12b-it-heretic-v2	![fp8][badge-fp8]	11.63 GB	![][gh-DreamFast]
gemma-3-12b-it-heretic-v2	![int8tensormixed][badge-int8tensormixed]	12.60 GB	![][gh-DreamFast]
gemma-3-12b-it-heretic-v2	![mxfp8mixed][badge-mxfp8mixed]	12.93 GB	![][gh-DreamFast]
gemma-3-12b-it-heretic-v2	![nvfp4][badge-nvfp4]	7.94 GB	![][gh-DreamFast]

GGUF

Quant	Size	Download
![F16][badge-F16]	22.45 GB	![][gh-DreamFast]
![Q8_0][badge-Q8_0]	11.93 GB	![][gh-DreamFast]
![Q6_K][badge-Q6_K]	9.21 GB	![][gh-DreamFast]
![Q5_K_M][badge-Q5_K_M]	8.05 GB	![][gh-DreamFast]
![Q5_K_S][badge-Q5_K_S]	7.85 GB	![][gh-DreamFast]
![Q4_K_M][badge-Q4_K_M]	6.96 GB	![][gh-DreamFast]
![Q4_K_S][badge-Q4_K_S]	6.61 GB	![][gh-DreamFast]
![Q3_K_M][badge-Q3_K_M]	5.73 GB	![][gh-DreamFast]

AX1Y2JP Ultra-Uncensored Heretic ComfyUI fp8_scaled

Ultra-uncensored fork of the Heretic encoder, fp8-scaled and ComfyUI-ready. Single safetensors by AX1Y2JP.

Model	Precision	Size	Download
gemma-3-12b-it-heretic (ultra-uncensored)	![fp8][badge-fp8]	12.99 GB	![][gh-AX1Y2JP]

mradermacher imatrix GGUF re-quant of Heretic v2 (24 quants)

Third-party imatrix (importance-matrix) re-quantization of DreamFast's Heretic v2 by mradermacher. Covers the full i1-IQ* and i1-Q_K family for low-VRAM use. Sizes verified from the repo file list.

Quant	Size	Download
![IQ1_M][badge-IQ1_M]	3.02 GB	![][gh-mradermacher]
![IQ1_S][badge-IQ1_S]	2.81 GB	![][gh-mradermacher]
![IQ2_M][badge-IQ2_M]	4.11 GB	![][gh-mradermacher]
![IQ2_S][badge-IQ2_S]	3.83 GB	![][gh-mradermacher]
![IQ2_XS][badge-IQ2_XS]	3.66 GB	![][gh-mradermacher]
![IQ2_XXS][badge-IQ2_XXS]	3.36 GB	![][gh-mradermacher]
![IQ3_M][badge-IQ3_M]	5.39 GB	![][gh-mradermacher]
![IQ3_S][badge-IQ3_S]	5.21 GB	![][gh-mradermacher]
![IQ3_XS][badge-IQ3_XS]	4.96 GB	![][gh-mradermacher]
![IQ3_XXS][badge-IQ3_XXS]	4.56 GB	![][gh-mradermacher]
![IQ4_NL][badge-IQ4_NL]	6.57 GB	![][gh-mradermacher]
![IQ4_XS][badge-IQ4_XS]	6.25 GB	![][gh-mradermacher]
![Q2_K][badge-Q2_K]	4.55 GB	![][gh-mradermacher]
![Q2_K_S][badge-Q2_K_S]	4.24 GB	![][gh-mradermacher]
![Q3_K_L][badge-Q3_K_L]	6.18 GB	![][gh-mradermacher]
![Q3_K_M][badge-Q3_K_M]	5.73 GB	![][gh-mradermacher]
![Q3_K_S][badge-Q3_K_S]	5.21 GB	![][gh-mradermacher]
![Q4_0][badge-Q4_0]	6.59 GB	![][gh-mradermacher]
![Q4_1][badge-Q4_1]	7.21 GB	![][gh-mradermacher]
![Q4_K_M][badge-Q4_K_M]	6.96 GB	![][gh-mradermacher]
![Q4_K_S][badge-Q4_K_S]	6.61 GB	![][gh-mradermacher]
![Q5_K_M][badge-Q5_K_M]	8.05 GB	![][gh-mradermacher]
![Q5_K_S][badge-Q5_K_S]	7.85 GB	![][gh-mradermacher]
![Q6_K][badge-Q6_K]	9.21 GB	![][gh-mradermacher]

▣ Gemma-4-12b (LTX-2.5 Text Encoders)

LTX-2.5 replaces the Gemma-3-12B text encoder with a Gemma-4-12B encoder. Community "heretic" / uncensored forks bypass alignment layers for maximum prompt fidelity in downstream video generation.

◦ Gemma-4-12b GGUF — elix3r low-VRAM quants

elix3r/gemma4-12b-with-proj-ltx-2.5-GGUF

elix3r/gemma4-12b-with-proj-ltx-2.5-GGUF — GGUF quants of the LTX-2.5 gemma4-12b text encoder (Q2_K / Q4_K_M / Q5_K_M) for ComfyUI-GGUF loading.

Quant	Size	Download
![Q2_K][badge-Q2_K]	5.96 GB	![elix3r][gh-elix3r]
![Q4_K_M][badge-Q4_K_M]	8.41 GB	![elix3r][gh-elix3r]
![Q5_K_M][badge-Q5_K_M]	9.51 GB	![elix3r][gh-elix3r]

◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆

▓ Separated Components

Separated LTX2 checkpoint by Kijai and Kijai for LTX-2.3. For alternative way to load the models in Comfy.

▣ Diffusion Models (Transformer Only)

[!NOTE]
input_scaled additionally have activation scaling, and are set to run with fp8 matmuls on supported hardware (roughly 40xx and later Nvidia GPUs).

▣ VAE (Video & Audio)

▣ Embedding Connectors & Text Projection

◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆

▓ LoRA

▣ Styles

• elismasilva
  • Latin Dance - Latin dance motion/style LoRA for LTX-2.3 (rank ~128). (214 MB)
• EllaPriest45
  • 3D Animation Style - 3D-rendered animation look for LTX-2.5 (t2v 0.8 str / i2v 0.4 str per filename). (674 MB)
• OmerHagawa
  • LTX2 UME PixelArt LoRA - Pixel art style LoRA for LTX-2
• Playtime-AI
  • Commission LTX-2.3 MtF Transformation - MtF transformation style LoRA for LTX 2.3
• Andro0s
  • Pixar Toon Style LoRA - Pixar-style CGI toon cinematic look with trigger word P1x4r
• Cseti
  • Arcane-Jinx v1 - Style LoRA inspired by Arcane's Jinx character design
  • ReStyle IC-LoRA - Image-guided style transfer IC-LoRA that re-renders videos in a target style while preserving original content and motion
• lopho
  • Gantz O v1.0.0 - Movie-style LoRA (654 MB, 10000 steps)
• bionicman69
  • Arnold Style - Arnold Style LoRA for LTX 2.3. Get to the choppa!
  • Star Trek TNG Style - Star Trek: The Next Generation style LoRA for LTX 2.3
• joeygambino
  • Surfaces Realism - Materials/realism LoRA (rank 32, video branch) that kills the "plastic" look: cracked wet asphalt stays cracked and wet, concrete gets pores and rust streaks, floors scuff, wood grains show. No trigger word — trains as unconditional LoRA behavior. Load at 1.0 and write prompts normally. (336 MB)
• CoachBate
  • Abercrom-ME - Vintage A&F Quarterly americana style-transfer IC-LoRA: transforms an input photo (subject + clothing + scene) into moody monochrome / sun-drenched beach / locker-room aesthetics with full styling makeover. Image-conditioned; pairs with the bundled ABERCROM-ME IC-LoRA by coachbate-v3_20steps_3phase_3stage3.json workflow. (384 MB, 2000 steps)
• ssjenforcer191
  • Homelander - Character IC-LoRA for The Boys' Homelander. Triggerword HeroHomelander (optionally append wearing red leather gloves / dark blue cape and ornate red-and-gold collar). Rank 64, 1500 steps, no regularization. Note: occasional letterbox black bars from training data. (~1.25 GB)
• oumoumad
  • LTX-2-19b-LoRA-SPROUT
  • Clay Stop Motion
• kabachuha
  • Hydraulic press
  • Cakeify
  • Big Anime Breasts
  • Eat
  • Squish – One Hand Only
  • POP! Inflatable Animation - Comically inflate and pop cartoon/anime characters into confetti and fabric scraps (I2V focused)
• CRT Animation Terminal by lovis93 - Real late-80s/early-90s CRT monitor look with scanlines, phosphor glow, chromatic aberration, and dithering. Trigger word: crtanim,. Available in 4000 and 10000 training steps variants
• vrgamedevgirl84 Style LoRAs
  • ClayMationStyle - Clay animation style LoRA for LTX-2.3
  • Wild West Style
  • Paper Cut Out Style
  • Post Apocalyptic Style
  • Pixar Toon Style
  • Luxe Sensual Style
  • Soft Enhance Style
  • Crisp Enhance Style
  • Fantasy Puppet Style
  • Fantasy Realism Style
  • Fantasy Painterly Style
  • Fantasy Anime Style
  • Cozy Felt Style
  • Clay Mation Style
  • 90s Animation Style
• Alissonerdx LTX-LoRAs Collection - Comprehensive collection including:
  • Anime2Half-Real - Converts anime-style content to half-realistic aesthetic (4500 steps, rank64)
  • Edit-Anything Global - Global editing LoRA variants (6000-9000 steps, rank128)
  • Inpaint Masked R2V/T2V - Region-based inpainting LoRAs for masked video editing
  • Real2Anime/Anime2Real - Style conversion LoRAs (rank64)
• Nebsh
  • Outfit Switch
  • Handheld run
  • Atomic Explosion
  • HERO CAM
  • Animatediff V1
  • PUSH TO GLASS
  • Object POV
• Squish
• Yoshiaki Kawajiri Retro Anime - LoRA trained on Yoshiaki Kawajiri's distinctive retro anime art style
• Playtime-AI
  • DonaldTrump
  • Rick_and_Morty - BETA LoRA for Rick and Morty animated style
  • LTX-2.3-Rick_And_Morty_v2 - Updated Rick and Morty v2 LoRA trained on the Smith and Rick Sanchez characters (undertrained; voices/clothing can be off; v3 in training)
  • LTX-2.3-Wednesday_Addams
  • LTX-2.3-Kermit_the_Frog
  • LTX-2.3-Jenna_Coleman
  • LTX-2.3-Marge_Simpson - Marge Simpson character LoRA trained on the base LTX-2.3 Dev model. Trigger words: 2d animation, Marge Simpson (use 2d animation to avoid getting 3D animation)
  • LTX-2.3-Bender - Bender (Futurama) character LoRA. Trigger words: 2d animation, Bender the bending robot
  • LTX-2.3 Sulphur Gyrating Hips - Motion LoRA driven by the trigger She thrusts her hips in a sexual manner
• SOLRICKS
  • LTX-2.3-Yesilcam-Turkish-Cinema - Nostalgic Yeşilçam Turkish cinema visual style with warm cinematic tones and classic film atmosphere. Recommended strength 0.7.
  • ltx-2-3-ue5-style-lora - Unreal Engine 5 (UE5) cinematic style LoRA. Trigger word: ue5_style.
  • Sci-Fi Cinema - a cinematic science-fiction style LoRA for LTXV / LTX-2.3. Trigger word: srx_scifilm.
  • LTX-2.3 Product Ad Style - Cinematic product-commercial style for luxury / cosmetics / tech / fashion ads. Trigger srx_commercial, recommended strength 0.85.
  • LTX-2.3 The Art of Marbling - Marbling / ebru ink-flow style (paper, pigment, fluid art, Turkish ebru). Trigger srx_ebrumotion, recommended strength 0.85.
  • LTX-2.5 BTS Movie Set - Cinematic behind-the-scenes movie-set atmosphere for LTX-2.5: professional camera rigs, cranes, dolly tracks, studio lighting, green/blue screens, practical sets and working film crews. T2V + I2V. (0.34 GB)
• SyFeee
  • ltx2.3-chinese-drama-charlora - Character LoRA trained on 78 episodes of Chinese historical drama; specialises base model for live-action, photoreal cinematic generation in Han dynasty / wuxia settings. Trigger words: char_0_person through char_9_person. Recommended strength 0.8–0.9.
  • ltx2.3-chinese-drama-iclora-canny - IC-LoRA conditioning on Canny edge/line-art video; controls scene composition and architectural layout from reference outlines. Use with char_0_person for character reference.
  • ltx2.3-chinese-drama-iclora-depth - IC-LoRA conditioning on monocular depth video (Depth-Anything-3); transfers 3D geometric structure from reference to generated video. Strong on interior scenes.
  • ltx2.3-chinese-drama-iclora-pose - IC-LoRA conditioning on DWPose 133-keypoint skeleton render; transfers pose from reference video while preserving Chinese drama style. Stackable with character LoRA.
  • LTX-2.3-SyFe-ID-LoRA - Identity (ID) LoRA for LTX-2.3 that preserves subject likeness / identity across frames. Two checkpoints (id_lora_ours_768, id_lora_ours_704), 1.16 GB each.
  • LTX-2.3-SyFe-Plain-AV-LoRA - Plain audio/video LoRA for LTX-2.3. Multiple checkpoints: production v1/v2 and bilingual (704) at ~0.86/0.43 GB, plus a unified v5 at 0.11 GB.
• mxturbo
  • Formula1-Cockpit-T-Cam-LTX2.3 - LoRA trained on 1.6L V6 Turbo Hybrid Era F1 T-Cam onboard footage. Generates cockpit/T-cam onboard video. Trigger: 16LV6HybridF1 (car type); follow the "T-cam onboard view..." / "AT-cam onboard view..." prompt style.
• chsengni
  • ltx2.3-fpv-motion - Smoother FPV (First Person View) camera movements and improved low-speed flight shots.
• EllaPriest45 — large LTX-2.3 / LTX-2.5 LoRA collections (NSFW actions / characters / styles / face-swap); open each repo for the full file list
  • LTX2.3_Actions — Huge collection of NSFW LoRAs for LTX-2.3 (179 .safetensors, ~137 GB): explicit action / motion / pose LoRAs. Pairs with 10Eros / Sulphur-2.
  • LTX2.3_Characters — Character LoRAs: massive per-celebrity likeness collection for LTX-2.3 (394 .safetensors, ~139 GB; each Name - LTX2.3.safetensors ~353 MB).
  • LTX2.3_Styles — Style LoRAs: large visual-style collection for LTX-2.3 (38 .safetensors, ~23 GB): anime, claymation, cyberpunk, post-apocalyptic, cozy felt, and more.
  • LTX2.5_actions (Best Face Swap) — LTX-2.5 face-swap LoRA collection (repo is a Civitai backup; credits to original authors). Two ranks: BFS - Best Face Swap R128 and BFS - Best Face Swap R64, 0.65 GB each (~1.3 GB total).
• Se0ulSeeker LTX-2.3 i2v NSFW LoRAs — A collection / list of NSFW i2v (image-to-video) LoRAs for LTX-2.3 (NSFW content only — do not use for clean content).
• lynaNSFW DR34ML4Y AIO NSFW LTX-2.3 — AIO (all-in-one) NSFW LoRA collection for LTX-2.3 with three versions (V1 / V2 / V3), 1.94 GB each (NSFW content only — do not use for clean content).
• TheBurgstall
  • LTX-2.3-Body-Positivity
  • LTX-2.3-Googly-Eyes
• TheBurgstall (LTX-2)
  • EarthZoomOut
  • GroupPhoto
  • WHATUSEE
• Black Venom
• Levmar
  • ltx2-lora — Image-to-Video LoRA fine-tuned from ltx-2.3-22b-dev.safetensors with the LTX LoRA Trainer (6000 steps, LR 1e-4, batch 1). Two checkpoints: lora_weights_step_02000.safetensors and lora_weights_step_06000.safetensors (~428 MB each). License: other.
• Lightricks
  • Camera Control: dolly-in
  • Camera Control: dolly-left
  • Camera Control: dolly-out
  • Camera Control: dolly-right
  • Camera Control: jib-down
  • Camera Control: jib-up
  • Camera Control: static
  • Union-Control
• eraRelentless
  • LTXreal - Realism stylization for LTX-2.3; trigger realism
• nnndite
  • ltx2.3 Foot Model - Foot / lower-limb LoRA for LTX-2.3
• fal
  • LTX-2.3 IC-LoRA — 3D Render to Photoreal - IC-LoRA turning rough 3D viewport / Blender blockouts into photoreal cinematic video while preserving composition and camera. Trigger 3DREAL. v2 (3DREAL-strong-v2) is the newest and is also exposed on fal.ai as render-to-real.
• a3xrfgb
  • Fable 5 — Vintage Style LoRA - Vintage-style minimal-illustration / stop-motion / typography LoRA for LTX-2.3, used in the Fable 5 intro. Trained on a personal RTX 3090 (~5 hours).
• AhsanHareem
  • ReelBids — LTX-2.5 dolly-in camera LoRA - Single rank-32 LoRA that drives a dolly-in camera move at seven selectable speeds for LTX-2.5 22B image-to-video. Speed is chosen by a trigger token in the prompt (sp05–sp50; e.g. sp20 ≈ 1.59× zoom over 97 frames), so one adapter covers the whole range. Best checkpoint at step 1250. (0.20 GB)

▣ Special & Enhancers

Combined table of enhancer, special, control, audio, camera, restoration and pipeline LoRAs, grouped into sub-tables by Type. (Ver = target LTX version: 2 / 2.3 / 2.5.)

❖ IC-LoRA · Control

❖ IC-LoRA · Restore

❖ IC-LoRA · Outpaint

❖ IC-LoRA · Relight

❖ IC-LoRA · Edit

❖ IC-LoRA · Effect

❖ Camera