Image-to-Video
Diffusers
LTX.io
text-to-video
video-to-video
image-text-to-video
audio-to-video
text-to-audio
video-to-audio
audio-to-audio
text-to-audio-video
image-to-audio-video
image-text-to-audio-video
ltx-2
ltx-video
ltxv
lightricks
ltx-2.3
Eval Results
Instructions to use Lightricks/LTX-2.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Lightricks/LTX-2.3 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image, export_to_video # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Lightricks/LTX-2.3", dtype=torch.bfloat16, device_map="cuda") pipe.to("cuda") prompt = "A man with short gray hair plays a red electric guitar." image = load_image( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png" ) output = pipe(image=image, prompt=prompt).frames[0] export_to_video(output, "output.mp4") - LTX.io
How to use Lightricks/LTX-2.3 with LTX.io:
# Install the LTX-2 pipelines git clone https://github.com/Lightricks/LTX-2.git cd LTX-2 uv sync --frozen
# Download the weights from this repo, plus the Gemma text encoder hf download Lightricks/LTX-2.3 --local-dir models/LTX-2.3 hf download google/gemma-3-12b-it-qat-q4_0-unquantized --local-dir models/gemma-3-12b
# Fast pipeline (distilled model, no distilled LoRA needed) uv run python -m ltx_pipelines.distilled \ --distilled-checkpoint-path models/LTX-2.3/<distilled-checkpoint>.safetensors \ --spatial-upsampler-path models/LTX-2.3/<spatial-upsampler>.safetensors \ --gemma-root models/gemma-3-12b \ --prompt "A beautiful sunset over the ocean" \ --output-path output.mp4 # For image-to-video, add: --image path/to/image.jpg 0 0.8# HQ pipeline (two-stage, higher quality) uv run python -m ltx_pipelines.ti2vid_two_stages_hq \ --checkpoint-path models/LTX-2.3/<checkpoint>.safetensors \ --distilled-lora models/LTX-2.3/<distilled-lora>.safetensors 0.8 \ --spatial-upsampler-path models/LTX-2.3/<spatial-upsampler>.safetensors \ --gemma-root models/gemma-3-12b \ --prompt "A beautiful sunset over the ocean" \ --output-path output.mp4 # For image-to-video, add: --image path/to/image.jpg 0 0.8 - Notebooks
- Google Colab
- Kaggle
json file reuired for this model is missing
1
#69 opened 1 day ago
by
mahendra0120
Some hard truths about data sourcing and the future of LTX
#68 opened 2 days ago
by
kabachuha
Upload IMG_20260724_204520_748.jpg
#67 opened 3 days ago
by
Shadowguy23
Clarification on LTX-2 Community License applicability to a public university
#66 opened 5 days ago
by
Bleusonnet
Community merge family built on LTX-2.3's audio branch + a working recipe for the x1.5 spatial upscaler's sequence-end corruption
1
#65 opened 13 days ago
by
joeygambino
I hope the author can change the behavior of LTXVAudioVAELoader so that it loads the file from the VAE instead of the checkpoint.
#63 opened 18 days ago
by
ovision
Question: custom LoRA trained on LTX 2.3 dev BF16 for distilled 1.1 FP8 inference
1
#62 opened 23 days ago
by
PatriciaScherer1
Any ETA for the Next Version or LTX2.5 ?
2
#61 opened 27 days ago
by
FP128765
with RTX 5090 200GB RAM - ltx 2.3 is broken
1
#60 opened about 1 month ago
by
hydraofm0
Mobile deployment question β can LTX-2.3 run on phones?
2
#59 opened about 1 month ago
by
3morixd
LTX-2.3
#58 opened about 1 month ago
by
R4PTORINF1LTR
Upload gemma-3-12b-it-abliterated_lora_rank64_bf16.safetensors
#57 opened about 1 month ago
by
Krnbhapkar0
Add WBench evaluation results
#56 opened 2 months ago
by
Kaining
Why is it impossible to control the volume of speaking characters?
1
#52 opened 2 months ago
by
plz12345
After recent study of bf16 accuracy issues, we need fp32
3
#48 opened 3 months ago
by
TenStrip
Update to spatial-upscaler-x1.5
π 1
1
#47 opened 3 months ago
by
RayRogala
Diffusers format
#44 opened 4 months ago
by
oglok
How to add BEEP sound effect for censored words?
1
#38 opened 4 months ago
by
jtreminio
Character LoRA severely reduces motion and ignores action prompts (ltx-2.3)
2
#36 opened 4 months ago
by
Spawn
LTX-2.3 temporal upscaler seems broken
4
#35 opened 4 months ago
by
oRELICo
Add model_index.json files for Diffusers compatibility
β 15
#31 opened 5 months ago
by
cjkindel
diffusers
π 2
3
#27 opened 5 months ago
by
ziwangfu
Swift MLX Support
π₯ 2
3
#22 opened 5 months ago
by
VincentGOURBIN
TX-2.3 model fails to load with Diffusers - Missing model_index.json
π 7
1
#20 opened 5 months ago
by
sachin915t
Render Times
8
#16 opened 5 months ago
by
DflippinK
Release for Diffusers?
π 6
8
#4 opened 5 months ago
by
tintwotin