RuneXX
/

LTX-2.3-Workflows

Model card Files Files and versions

Instructions to use RuneXX/LTX-2.3-Workflows with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RuneXX/LTX-2.3-Workflows with LTX-2:

# Install the LTX-2 pipelines
git clone https://github.com/Lightricks/LTX-2.git
cd LTX-2
uv sync --extra natten

# Download weights from this repo
# Substitute filenames from this repo's "Files and versions" if they differ
hf download RuneXX/LTX-2.3-Workflows \
    diffusion_models/<distilled-transformer>.safetensors \
    text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors \
    vae/<video-vae>.safetensors \
    vae/<audio-vae>.safetensors \
    latent_upscale_models/<spatial-upsampler>.safetensors \
    latent_upscale_models/<temporal-upsampler>.safetensors \
    --local-dir models/LTX-2.3-Workflows
# DFR requires the detailing IC-LoRA (separate repo; strength is fixed at 0.5)
hf download Lightricks/LTX-2.5-22b-IC-LoRA-Pixel-Spatial-Upscaler --local-dir models/LTX-2.5-22b-IC-LoRA-Pixel-Spatial-Upscaler

# Distilled LTX-2.5 pipeline (fast)
uv run python -m ltx_pipelines.distilled \
    --transformer-path models/LTX-2.3-Workflows/diffusion_models/<distilled-transformer>.safetensors \
    --text-encoder-path models/LTX-2.3-Workflows/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors \
    --video-vae-path models/LTX-2.3-Workflows/vae/<video-vae>.safetensors \
    --audio-vae-path models/LTX-2.3-Workflows/vae/<audio-vae>.safetensors \
    --spatial-upsampler-path models/LTX-2.3-Workflows/latent_upscale_models/<spatial-upsampler>.safetensors \
    --num-frames 121 \
    --prompt "A beautiful sunset over the ocean" \
    --output-path output.mp4
# For image-to-video, add: --image path/to/image.jpg 0 0.8

# DFR pipeline (higher detail fidelity; optional temporal 2x/4x)
uv run python -m ltx_pipelines.dfr_pipeline \
    --transformer-path models/LTX-2.3-Workflows/diffusion_models/<distilled-transformer>.safetensors \
    --text-encoder-path models/LTX-2.3-Workflows/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors \
    --video-vae-path models/LTX-2.3-Workflows/vae/<video-vae>.safetensors \
    --audio-vae-path models/LTX-2.3-Workflows/vae/<audio-vae>.safetensors \
    --spatial-upsampler-path models/LTX-2.3-Workflows/latent_upscale_models/<spatial-upsampler>.safetensors \
    --temporal-upsampler-path models/LTX-2.3-Workflows/latent_upscale_models/<temporal-upsampler>.safetensors \
    --detailing-lora models/LTX-2.5-22b-IC-LoRA-Pixel-Spatial-Upscaler/ltx-2.5-22b-ic-lora-pixel-spatial-upscaler-x2-1.0.safetensors \
    --spatial-upscalings 1 \
    --temporal-upscalings 1 \
    --height 1088 \
    --width 1920 \
    --num-frames 121 \
    --prompt "A beautiful sunset over the ocean" \
    --output-path output.mp4
# For 4K: --spatial-upscalings 2 --width 3840 --height 2176
# For image-to-video, add: --image path/to/image.jpg 0 0.8

Notebooks
Google Colab
Kaggle

Resources

View closed (33)

Where to find files, loras, nodes and other resources - Awesome LTX

#199 opened about 1 month ago by

Where to save the files

#10 opened 6 months ago by

Workflow - update/change log

#7 opened 6 months ago by

Are you perhaps planning to adapt V2V - Extend Any Video wf to Minimax H3? :-)

#213 opened 6 days ago by

ideaszemetetmind

What about LTX-2.5? Is there a big difference compared to LTX-2.3?

#212 opened 21 days ago by

RuneXX discord?

#211 opened 21 days ago by

LTX 2.5

#210 opened 22 days ago by

Same workflows for 2.5

#209 opened 23 days ago by

LTX 2.5 is out!!!! RUNE!! Are you making WF for LTX 2.5 already?

#208 opened 23 days ago by

Workflows Speed Optimization

#207 opened 23 days ago by

How to replace dialogues wirh same voice and tone in existing video?

#206 opened 27 days ago by

how to keep consistant face in LTX-2.3_-_V2V_inpainting_Inpaint-T2V-lora_Sam3-Masking.json

#205 opened 29 days ago by

Multi-reference workflow input format

#204 opened about 1 month ago by

Will you make workflows for Minimax H3?

#203 opened about 1 month ago by

RUNE XX WORKFLOWS vs nomadoor WORKFLOWS

#202 opened about 1 month ago by

Workflow - V2V General Purpose for most IC-Loras (colorization, clean plate, water sim, black magic, deblur, cinemagraph, day-to-night etc....)

#201 opened about 1 month ago by

LTX-2.3_-_T2V_R2V_character-sheet_Best-Face-ID-Lora.json

#200 opened about 1 month ago by

JoyAI Echo Surgical Merge

#198 opened about 1 month ago by

LTX-2.3-22b-IC-LoRA-Colorization

#197 opened about 1 month ago by

Workflow - V2A - Add sound to any silent video with LTX Foley Lora.

#196 opened about 1 month ago by

Workflow - V2V Upscale Any Video with Pixel Spatial Lora

#195 opened about 1 month ago by

Workflow: V2V - Mass remove people and moving object from a video with Clean Plate Lora

#194 opened about 1 month ago by

Workflow: T2V R2V - Create consistent character videos from a reference face image with Best Face ID lora

#193 opened about 2 months ago by

Extend Video Workflow

#192 opened about 2 months ago by

Face id lora can work for multi characters?

#191 opened about 2 months ago by

Workflow : V2V - Create a new viewpoint angle from any video with CrossView Lora

#190 opened about 2 months ago by

Workflow: I2V Multi-Subject Reference with Licon MSR V2 Lora

#189 opened about 2 months ago by

LTX-2.3_-_I2V_multi-subject-reference_Licon-MSR-lora Changes character completly

#188 opened about 2 months ago by

Workflow: T2V R2V Character Sheet with Best Face ID Lora

#187 opened about 2 months ago by

LTX-2.3_-_FLF2V_First-Last-Frame Prompt Enhancer cannot be disabled

#186 opened about 2 months ago by

Does ModelSamplingSD3 do anything? DevModel WF.

#185 opened about 2 months ago by

RUNE - Do you have a WF that can change the face of a person in a video, using an INPUT IMAGE of another person?

#182 opened 2 months ago by

error for v2v extended: RuntimeError: cannot reshape tensor of 0 elements into shape [-1, 0] because the unspecified dimension size -1 can be any value and is ambiguous

#181 opened 2 months ago by

License clarification for workflow JSON files

#180 opened 2 months ago by

LTXV Context Windows

#179 opened 2 months ago by

Patiently waiting for workflow for the new LTX loras

#178 opened 3 months ago by

help me use runninghub for workflow so confused

#176 opened 3 months ago by

Licon MSR Lora + LTX Director

#175 opened 3 months ago by

sugarcoatarttech

Does anyone know if RuneXX has a similar WF to Control-reference

#174 opened 3 months ago by

LTX-2.3_-_I2V_multi-subject-reference_Licon-MSR-lora ValueError: guide pre_filter_counts (1320) != keyframe grid mask length (1980)

#173 opened 3 months ago by

Bernini Workflow

#172 opened 3 months ago by

Seed Hunting Workflow

#171 opened 3 months ago by

Thank you!

#170 opened 3 months ago by

LTX-2.3_-_FLF2V_First-Last-Frame_custom_audio 48fps?

#169 opened 3 months ago by

Is "LTX-2.3_-_I2V_T2V_Long_Video_Custom_Audio_Loop.json" possible with Prompt Relay?

#168 opened 3 months ago by

Workflow - I2V Multi-Subject Reference with Licon-MSR lora

#167 opened 3 months ago by

What is the best workflow + lora combination for simple text to video prompt with proper lip movement and audio genereation?

#166 opened 3 months ago by

LTX2.3-Mutiple-Subject-Reference (new IC lora model)

#164 opened 3 months ago by

Workflow - V2V inpainting with Inpaint-Masked-T2V Lora

#163 opened 3 months ago by

Is there any video inpaint workflow?

#162 opened 3 months ago by