awesome-ltx2

Awesome LTX-2

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

[![Telegram][telegram-shield]][telegram-url] [![X][x-shield]][x-url]

• Apps & Tools
• Models
  • Checkpoints
    • silveroxides Quantizations (mxfp8)
    • Distilled LoRA
    • TenStrip Distilled LoRA Experiments
    • Spatial Upscaler
    • Temporal Upscaler
  • Merges
  • Finetunes
    • DaSiWa
    • 10Eros
    • 10Eros Max (MiniMax-H3 grafts)
    • Sulphur-2-base
    • PinkCherry NSFW
    • colinb83 NSFW (LTX-2.5 full FT)
    • Stubelius Remix (Stuubs)
    • EllaPriest45 (model mirror)
  • GGUF Quantized Models
  • MLX (Apple Silicon)
• Text Encoders
  • Comfy-Org Optimized Encoders
  • Gemma-3-12b-it GGUF (stock encoder)
  • Gemma-3-12b-it QAT (Lightricks)
  • Gemma-3-12b Abliterated
  • Gemma-3-12b IT Heretic
  • Gemma-4-12b (LTX-2.5 Text Encoders)
• Separated Components
  • Diffusion Models (Transformer Only)
  • VAE (Video & Audio)
  • Embedding Connectors & Text Projection
  • LTX-2.5 Diffusers Layout (Lightricks)
  • LTX-2.5 Diffusers Layout (Rin247 MECHA Forge quants)
• 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
  • TenStrip
  • CQdesign
  • Ydudjsb
  • 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)

LTX-2 Marking (VideoSeal / PixelSeal / AudioSeal)

The weights and configs for the opt-in, post-hoc invisible marking used by LTX-2: PixelSeal (VideoSeal family) for video frames and AudioSeal for stereo PCM. MIT licensed, pytorch library. This is not a generator model - there is nothing to run or train against it, only to download.

File	Purpose	Size	Download
pixelseal.pth	PixelSeal embedder + extractor weights (256-bit payload, 256 px processing size)	308.95 MB	![][gh-Lightricks]
audioseal_generator.pth	AudioSeal 16-bit generator (embed)	58.81 MB	![][gh-Lightricks]
audioseal_detector.pth	AudioSeal 16-bit detector	34.67 MB	![][gh-Lightricks]

How it fits together - the LTX-2 loader (create_markers) requires all five model files (the three above plus pixelseal.yaml, the PixelSeal model card describing the architecture, and videoseal_attenuation.yaml, the JND attenuation channel map) in one directory; the code that embeds and detects lives in packages/ltx-pipelines/src/ltx_pipelines/marking in the LTX-2 repo. The .pth files are PyTorch pickles - verify the SHA-256 sums printed on the model card after download.

Enable it with --marker-root-path path/to/marking on the generation, editing and text-to-audio CLIs; omit the flag to leave pixels and PCM unchanged. Video generation and the HDR paths mark video while the text-to-audio path marks only audio, and detection returns MarkDetectResult(detected, bit_accuracy, p_value, payload) - video marks are judged on every 8th decoded frame at log10(p_value) < -6, audio over the full stereo track.

◦ The marks are a robust invisible signal, not a cryptographic signature: a detected mark means the clip came from an LTX-2 pipeline with marking enabled, while the absence of a mark does not prove a clip was not generated.

▓ 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
• unsloth - Quantized dev / distilled DiTs (FP8, INT8, INT8-ConvRot) + GGUF quants

Ver	Name	Precision	Size	Download
2.5	dev	![bf16][badge-bf16]	42.02 GB	![][gh-Lightricks]
2.5	dev		21.50 GB	![][gh-Lightricks]
2.5	distilled	![bf16][badge-bf16]	42.02 GB	![][gh-Lightricks]
2.5	distilled		21.50 GB	![][gh-Lightricks]
2.5	distilled	![nvfp4][badge-nvfp4]	18.72 GB	![][gh-Lightricks]
2.5	pt (pre-trained)	![bf16][badge-bf16]	46.2 GB	![][gh-Lightricks]
2.5	distilled	![nvfp4][badge-nvfp4]	22.1 GB	![][gh-rockerBOO]
2.5	dev		12.52 GB	![][gh-Winnougan]
2.5	distilled		12.52 GB	![][gh-Winnougan]
2.5	distilled	![fp8][badge-fp8]	21.03 GB	![][gh-vonkaiser]
2.5	distilled	![nvfp4][badge-nvfp4]	18.7 GB	![][gh-BennyDaBall]
2.5	dev		15.4 GB	![][gh-tsolful]
2.5	distilled		15.4 GB	![][gh-tsolful]
2.5	distilled	![fp8][badge-fp8]	23.5 GB	![][gh-guillaume127]
2.5	dev		21.64 GB	![][gh-DmitryDB]
2.5	dev	![nvfp4][badge-nvfp4]	13.57 GB	![][gh-DmitryDB]
2.5	distilled		21.64 GB	![][gh-DmitryDB]
2.5	distilled	![nvfp4][badge-nvfp4]	13.57 GB	![][gh-DmitryDB]
2.5	distilled		25.11 GB	![][gh-Unsloth]
2.5	distilled	![fp8][badge-fp8]	19.06 GB	![][gh-Unsloth]
2.5	distilled		25.11 GB	![][gh-Unsloth]
2.3	dev	![bf16][badge-bf16]	46.1 GB	![][gh-Lightricks]
2.3	dev	![fp8][badge-fp8]	29.1 GB	![][gh-Lightricks]
2.3	dev	![fp8][badge-fp8]	29.9 GB	![][gh-drbaph]
2.3	dev	![int8mixedrowwise][badge-int8mixedrowwise]	29.2 GB	![][gh-Winnougan]
2.3	dev	![nvfp4][badge-nvfp4]	21.7 GB	![][gh-Lightricks]
2.3	dev	![fp8][badge-fp8]	29.1 GB	![][gh-Lightricks]
2.3	distilled	![bf16][badge-bf16]	46.1 GB	![][gh-Lightricks]
2.3	distilled	![fp8][badge-fp8]	29.5 GB	![][gh-Lightricks]
2.3	distilled	![fp8][badge-fp8]	29.9 GB	![][gh-drbaph]
2.3	distilled	![int8tensormixed][badge-int8tensormixed]	29.1 GB	![][gh-Winnougan]
2.3	distilled	![nvfp4][badge-nvfp4]	17.6 GB	![][gh-Winnougan]
2.3	distilled	![mxfp8mixed][badge-mxfp8mixed]	29.7 GB	![][gh-silveroxides]
2.3	distilled 1.1	![bf16][badge-bf16]	46.1 GB	![][gh-Lightricks]
2.3	distilled 1.1		16.65 GB	![][gh-JoaoZaokk]
2.3	distilled 1.1		15.37 GB	![][gh-JoaoZaokk]
2.3	ltx23_srx fp8_e4m3 experimental	![fp8][badge-fp8]	23.1 GB	![][gh-SOLRICKS]
2.3	distilled	![fp8][badge-fp8]	19.06 GB	![][gh-Unsloth]
2.3	distilled		19.32 GB	![][gh-Unsloth]
2	ltx-2-19b dev	![bf16][badge-bf16]	43.3 GB	![][gh-Lightricks]
2	ltx-2-19b dev	![fp8][badge-fp8]	27.1 GB	![][gh-Lightricks]
2	ltx-2-19b dev	![fp4][badge-fp4]	20 GB	![][gh-Lightricks]
2	ltx-2-19b distilled	![bf16][badge-bf16]	43.3 GB	![][gh-Lightricks]
2	ltx-2-19b distilled	![fp8][badge-fp8]	27.1 GB	![][gh-Lightricks]
2	ltx-2-19b distilled	![nvfp4][badge-nvfp4]	20 GB
2	ltx-2-19b dev	![fp8][badge-fp8]	18.91 GB	![][gh-Unsloth]
2	ltx-2-19b dev		19.09 GB	![][gh-Unsloth]

◦ unsloth quant rows — pre-quantized DiTs built from the diffusers-format releases (torchao layout; loaded strictly by diffusers / Unsloth Studio — not ComfyUI single-file diffusion_models/ weights). Each file is bit-identical to quantizing the dense bf16 weights on the fly, so it skips the dense load + quantize step. Repos: LTX-2-FP8 (dev + pre-cast fp8 text encoder) · LTX-2.3-FP8 (distilled + bf16 originals) · LTX-2.5-FP8 (distilled; INT8-ConvRot recommended).

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

Ver	Name	Precision	Size	Download
2	ltx-2-19b dev		27.1 GB

❖ 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.

Ver	Name	Precision	Size	Download
2.3	image dev	![bf16][badge-bf16]	33.61 GB	![elismasilva][gh-elismasilva]
2.3	image distilled	![bf16][badge-bf16]	33.61 GB	![elismasilva][gh-elismasilva]
2.3	image dev		21.81 GB	![elismasilva][gh-elismasilva]
2.3	image distilled		21.81 GB	![elismasilva][gh-elismasilva]

❖ 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.

Model	Quant	Size	Download
ltx-2.3-22b-dev	![int8mixedtensorwise][badge-int8mixedtensorwise]	29.2 GB	![][gh-silveroxides]
ltx-2.3-22b-distilled	![int8tensormixed][badge-int8tensormixed]	29.1 GB	![][gh-silveroxides]
ltx-2.3-22b-distilled	![int8mixedtensorwise][badge-int8mixedtensorwise]	29.2 GB	![][gh-silveroxides]
ltx-2.3-22b-distilled	![mxfp8mixed][badge-mxfp8mixed]	29.7 GB	![][gh-silveroxides]

❖ Distilled LoRA

Ver	Rank	Precision	Size	Download
2.5	450	![bf16][badge-bf16]	8.90 GB	![][gh-Lightricks]
2.5	450		5.06 GB	![][gh-DmitryDB]
2.5	450	![nvfp4][badge-nvfp4]	2.66 GB	![][gh-DmitryDB]
2.5	450	![bf16][badge-bf16]	8.90 GB	![][gh-rzgar]
2.5	384	![bf16][badge-bf16]	7.61 GB	![][gh-rzgar]
2.5	256	![bf16][badge-bf16]	5.10 GB	![][gh-rzgar]
2.5	256	![bf16][badge-bf16]	5.10 GB	![][gh-TheDivergentAI]
2.5	128	![bf16][badge-bf16]	2.58 GB	![][gh-TheDivergentAI]
2.5	64	![bf16][badge-bf16]	1.32 GB	![][gh-TheDivergentAI]
2.5	128	![bf16][badge-bf16]	2.31 GB	![][gh-pyros-vault]
2.5	72	![bf16][badge-bf16]	1.38 GB	![][gh-pyros-vault]
2.5	256	![bf16][badge-bf16]	4.01 GB	![][gh-ibyteohdear]
2.5	96	![bf16][badge-bf16]	1.80 GB	![][gh-ibyteohdear]
2.5	32	![bf16][badge-bf16]	0.66 GB	![][gh-ibyteohdear]
2.3	384	![bf16][badge-bf16]	7.61 GB	┊
2.3	208	![bf16][badge-bf16]	4.97 GB	![][gh-drbaph]
2.3	159	![bf16][badge-bf16]	3.83 GB	![][gh-drbaph]
2.3	111	![bf16][badge-bf16]	2.74 GB	┊
2.3	105	![bf16][badge-bf16]	2.59 GB	![][gh-Kijai]
2	384	![bf16][badge-bf16]	7.67 GB	![][gh-Lightricks]
2	242	![bf16][badge-bf16]	4.88 GB	![][gh-Kijai]
2	175	![bf16][badge-bf16]	3.58 GB	![][gh-Kijai]
2	175	![fp8][badge-fp8]	1.79 GB	![][gh-Kijai]

◦ Rank-reduced 2.5 builds - the canonical source is the official Lightricks/LTX-2.5/loras/ltx-2.5-22b-distilled-lora-450-bf16.safetensors (8.90 GB, rank 450). The ibyteohdear reduced variants rerank that file with a factored SVD (rerank_method: factored_svd, source lora_rank: 450) and then cap the result at 32 / 96 / 256 - the ceil suffix is that ceiling and fro90 the singular-value floor (same scheme as pyros-vault).

❖ 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.

Name	Rank	Mode	Size	Download
distilled v1.1	32	condsafe	380 MB	![TenStrip][gh-TenStrip]
distilled v1.1	36	—	739 MB	![TenStrip][gh-TenStrip]
distilled v1.1	52	condsafe	487 MB	![TenStrip][gh-TenStrip]
distilled v1.1	72	condsafe	662 MB	![TenStrip][gh-TenStrip]
distilled	72	—	1.4 GB	![TenStrip][gh-TenStrip]
distilled v1.1	72	energy	1.72 GB	![TenStrip][gh-TenStrip]
distilled v1.1	96	energy	2.28 GB	![TenStrip][gh-TenStrip]

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.

Ver	Name	Size	Download
2.5	spatial-upscaler x2 1.0	995.78 MB	![][gh-Lightricks] ┊ ![][gh-ChrisColeTech]
2.3	spatial-upscaler x2 1.0	996 MB	![][gh-ChrisColeTech]
2.3	spatial-upscaler x2 1.1	996 MB	![][gh-Lightricks] ┊ ![][gh-ChrisColeTech]
2.3	spatial-upscaler x1.5 1.0	1.09 GB	![][gh-Lightricks]
2	spatial-upscaler x2 1.0	995.77 MB	![][gh-Lightricks]

⚠️ The official ltx-2.3-spatial-upscaler-x2-1.0.safetensors was deleted upstream from Lightricks/LTX-2.3; only the ChrisColeTech mirror still carries the 1.0 build. The upstream successor is x2 1.1 (linked above) — the repo now ships x1.5 1.0 and x2 1.1 only.

❖ Temporal Upscaler

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

Ver	Name	Size	Download
2.5	temporal-upscaler x2 1.0	0.26 GB	![][gh-Lightricks] ┊ ![][gh-ChrisColeTech]
2.3	temporal-upscaler x2 1.0	262 MB	![][gh-Lightricks]
2	temporal-upscaler x2 1.0	262 MB	![][gh-Lightricks]

▣ Merges

Custom merged models combining multiple control signals or specialized configurations.

Ver	Name	Description	Download
2.3	ltx-2.3-22b-distilled-1.1-fused-union-control	Merged model combining Canny, Depth, and Pose control signals for unified control
2.5	Alpha-Gen VideoOnly48 NVFP4	Official Alpha-Gen IC-LoRA merged into the base weights at strength 1.0, then structurally pruned to 48 blocks and quantized to NVFP4 with dynamic activation scales. Ships no LoRA — the matting behaviour is in the checkpoint. Ships a provenance.json with base/alpha SHA-256 and a full quality-vs-teacher report.

◦ mskim8584 caveats — read provenance.json before trusting it. The producer's own audit reports "quality_accepted": false and "accepted": false: whole-frame MAE 0.0059, PSNR 30.8 dB, SSIM 0.972, gradient MAE 0.0042, temporal flicker MAE 0.0034, temporal-boundary MAE 0.0416. catastrophic_inversion_frame_count is 0, so nothing blew up, but both the BF16 intermediate and the NVFP4 pass were explicitly marked as not accepted quality. The BF16 merge also required cached_final_empty_prompt_required conditioning and was fused on CPU. Treat as an experiment, not a drop-in replacement for the LoRA.

▣ 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.

Ver	Build	Name	Precision	Size	Download
2.3	Distilled	Treasurechest V1	![fp8][badge-fp8]	21.02 GB	![DaSiWa][gh-DaSiWa]
2.3	Distilled	Solsticecoin V2	![fp8][badge-fp8]	30.13 GB	![DaSiWa][gh-DaSiWa]
2.3	Distilled	Dragonleap V4	![int4mixedtensorwise][badge-int4mixedtensorwise]	18.38 GB	![DaSiWa][gh-DaSiWa]
2.3	Distilled	Dragonleap V4	![int8tensormixed][badge-int8tensormixed]	27.64 GB	![DaSiWa][gh-DaSiWa]
2.3	Non-Distilled	GoldenLace V3	![fp8][badge-fp8]	29.16 GB	![DaSiWa][gh-DaSiWa]
2.3	Non-Distilled	GoldenLace V3	![nvfp4][badge-nvfp4]	21.73 GB	![DaSiWa][gh-DaSiWa]
2.3	Non-Distilled GGUF	GoldenLace V3	![Q2_K][badge-Q2_K]	8.51 GB	![DaSiWa][gh-DaSiWa]
2.3	Non-Distilled GGUF	GoldenLace V3	![Q3_K_M][badge-Q3_K_M]	10.6 GB	![DaSiWa][gh-DaSiWa]
2.3	Non-Distilled GGUF	GoldenLace V3	![Q4_K_M][badge-Q4_K_M]	13.33 GB	![DaSiWa][gh-DaSiWa]
2.3	Non-Distilled GGUF	GoldenLace V3	![Q5_K_M][badge-Q5_K_M]	15.9 GB	![DaSiWa][gh-DaSiWa]
2.3	Non-Distilled GGUF	GoldenLace V3	![Q6_K][badge-Q6_K]	18.63 GB	![DaSiWa][gh-DaSiWa]
2.3	Non-Distilled GGUF	GoldenLace V3	![Q8_0][badge-Q8_0]	23.61 GB	![DaSiWa][gh-DaSiWa]

DaSiWa extracted LoRA:

Build	Name	LoRA Rank	Size	Download
DMD v2 audio	LTX2.3_DMD_v2_avgrank86_audio160_L80-D20	86 (audio 160)	2.27 GB	![DaSiWa][gh-DaSiWa]

❖ 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.

Ver	Build	Name	Precision	Size	Download
2.3	Full	10Eros v1	![bf16][badge-bf16]	46.14 GB	![TenStrip][gh-TenStrip]
2.3	Full	10Eros v1	![fp8][badge-fp8]	29.16 GB	![TenStrip][gh-TenStrip]
2.3	transformer-only	10Eros v1	![fp8][badge-fp8]	29.56 GB	![TenStrip][gh-TenStrip]
2.3	Full	10Eros v1.2	![bf16][badge-bf16]	46.14 GB	![TenStrip][gh-TenStrip]
2.3	Full	10Eros v1.2	![fp8][badge-fp8]	34.33 GB	![TenStrip][gh-TenStrip]
2.3	Full	10Eros v1.3	![bf16][badge-bf16]	46.14 GB	![TenStrip][gh-TenStrip]
2.3	Full	10Eros v1.3	![fp8][badge-fp8]	29.16 GB	![TenStrip][gh-TenStrip]
2.3	Full	10Eros v1.4	![bf16][badge-bf16]	46.14 GB	![TenStrip][gh-TenStrip]
2.3	Full	10Eros v1.4	![fp8][badge-fp8]	29.16 GB	![TenStrip][gh-TenStrip]
2.3	Full	10Eros v1.4 DMD int8 ConvRot	![int8tensormixed][badge-int8tensormixed]	29.16 GB	![TenStrip][gh-TenStrip]
2.3	Full	10Eros v1.5	![bf16][badge-bf16]	46.14 GB	![TenStrip][gh-TenStrip]
2.3	Full	10Eros v1.5 DMD int8	![int8tensormixed][badge-int8tensormixed]	29.16 GB	![CornLogic][gh-CornLogic]
2.3	transformer-only	10Eros v1.5 DMD int8	![int8tensormixed][badge-int8tensormixed]	25.03 GB	![CornLogic][gh-CornLogic]
2.3	transformer-only	10Eros v1.5 int8	![int8tensormixed][badge-int8tensormixed]	25.03 GB	![CornLogic][gh-CornLogic]
2.3	Full	10Eros v1.5 fp8mixed (experimental, learned)	![fp8][badge-fp8]	30.24 GB	![LokkenJP][gh-LokkenJP]
2.3	Full	10Eros v1 INT8 ConvRot		23.51 GB	![milo01][gh-milo01]

◦ The 10Eros Max line is a different architecture — see ❖ 10Eros Max (MiniMax-H3 grafts) below. The gated TenStrip/LTX2.3-10Eros_Version-Testing repo despite its name holds MiniMax-H3 (Hailuo 3) grafts, not LTX-2.3 DiTs. Everything in the table above is a genuine LTX-2.3 AVTransformer3DModel checkpoint (model.diffusion_model + vocoder + vae + audio_vae, 23.07 B params).

◦ 10Eros v1.5 companions — the int8 and fp8mixed v1.5 builds live in third-party repos: CornLogic/10EROS-INT8 (full int8 checkpoint + two transformer-only variants) and LokkenJP/10EROS_1.5_fp8_exp_learned (fp8mixed, experimental, with a .quantization.json + .sha256 sidecar).

◦ 10Eros v1 INT8 ConvRot mirror — the original bertbobson/LTX2.3-10Eros-INT8-ConvRot repo is no longer public (the API returns Invalid username or password and it is absent from the author's model list). The row above points at the public milo01/LTX2.3-10Eros-INT8-ConvRot mirror, which carries the identically-named file at the same byte size. Other public mirrors: Winnougan/10Eros-INT8-Convrot (v1.2), CornLogic/10EROS_1.4_Int8_ConvRot and chfm/10EROS_1.4_Int8_ConvRot (v1.4, both).

◦ 10Eros GGUF — vantagewithai low-VRAM quants

vantagewithai/LTX2.3-10Eros-GGUF — v1

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]	13.9 GB	![vantagewithai][gh-vantagewithai]
![Q4_K_M][badge-Q4_K_M]	14.3 GB	![vantagewithai][gh-vantagewithai]
![Q4_K_S][badge-Q4_K_S]	13.2 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]

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]	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]	13.9 GB	![vantagewithai][gh-vantagewithai]
![Q4_K_M][badge-Q4_K_M]	14.3 GB	![vantagewithai][gh-vantagewithai]
![Q4_K_S][badge-Q4_K_S]	13.2 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]

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

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]	13.9 GB	![vantagewithai][gh-vantagewithai]
![Q4_K_M][badge-Q4_K_M]	14.3 GB	![vantagewithai][gh-vantagewithai]
![Q4_K_S][badge-Q4_K_S]	13.2 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]

vantagewithai/LTX2.3-10Eros-1.4-GGUF — v1.4 (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]	13.9 GB	![vantagewithai][gh-vantagewithai]
![Q4_K_M][badge-Q4_K_M]	14.3 GB	![vantagewithai][gh-vantagewithai]
![Q4_K_S][badge-Q4_K_S]	13.2 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]

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

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

Component	Precision	Size	Download
Model	![bf16][badge-bf16]	42.01 GB	![vantagewithai][gh-vantagewithai]
Model	![fp8][badge-fp8]	28.28 GB	[![vantagewithai][gh-vantagewithai]](https://huggingface.co/vantagewithai/LT