Instructions to use SagiPolaczek/LTX-2.3-Sync-LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use SagiPolaczek/LTX-2.3-Sync-LoRA 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", torch_dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("SagiPolaczek/LTX-2.3-Sync-LoRA") prompt = "A man with short gray hair plays a red electric guitar." input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png") image = pipe(image=input_image, prompt=prompt).frames[0] export_to_video(output, "output.mp4") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
What exactly does/can this do?
#1
by gpundt - opened
So could this theoretically remove objects from videos if you upload an edited first frame with an object removed?
correct!
Try it and let me know how it goes
Is there a simple workflow for this?
Should work with existing workflows of LTX-2 where they use IC-LoRA for conditional generation.
Note the prompt β3d1tβ (see README)
So in comfy you plug edited first frame in i2v and unedited video correct ?
correct, let me know how it works!
if it doesn't work, i will publish one myself
Tried a lot but couldnt make it work. As you mentioned, can you please publish a comfyui workflow for it?
workflow, please
Yes, a simple workflow would be great. Thank You.
Workflow, I can't make it work! Thanks