Instructions to use realrebelai/LTX-2.5_GGUFs with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use realrebelai/LTX-2.5_GGUFs 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 realrebelai/LTX-2.5_GGUFs \
    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-2.5_GGUFs
# 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-2.5_GGUFs/diffusion_models/<distilled-transformer>.safetensors \
    --text-encoder-path models/LTX-2.5_GGUFs/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors \
    --video-vae-path models/LTX-2.5_GGUFs/vae/<video-vae>.safetensors \
    --audio-vae-path models/LTX-2.5_GGUFs/vae/<audio-vae>.safetensors \
    --spatial-upsampler-path models/LTX-2.5_GGUFs/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-2.5_GGUFs/diffusion_models/<distilled-transformer>.safetensors \
    --text-encoder-path models/LTX-2.5_GGUFs/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors \
    --video-vae-path models/LTX-2.5_GGUFs/vae/<video-vae>.safetensors \
    --audio-vae-path models/LTX-2.5_GGUFs/vae/<audio-vae>.safetensors \
    --spatial-upsampler-path models/LTX-2.5_GGUFs/latent_upscale_models/<spatial-upsampler>.safetensors \
    --temporal-upsampler-path models/LTX-2.5_GGUFs/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

Running ON <4gb Vram

by Jit2024 - opened Sep 10

Discussion

Jit2024

Sep 10

Hi, I found out a way of running this model on <4gb Vram. And I have not used any quantization.
Repo: https://github.com/Jit-Roy/WeeLLM

realrebelai

Owner Sep 10

Hi, I found out a way of running this model on <4gb Vram. And I have not used any quantization.
Repo: https://github.com/Jit-Roy/WeeLLM

Great work brother! Ill check it out today! Ive been waiting for something like this 🤝🔥

ARandomCoder2026

Sep 10

•

This comment has been hidden (marked as Resolved)

ARandomCoder2026

Sep 10

Hi, I found out a way of running this model on <4gb Vram. And I have not used any quantization.
Repo: https://github.com/Jit-Roy/WeeLLM

I tried out the image models and they’re working perfectly! 😭

Never thought I’d be able to run Qwen-Image on just 4GB VRAM lol. This is actually insane. Thanks for making this!

jsob7

15 days ago

wow this is interesting i'm gonna check it out

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment