Instructions to use Lightricks/LTX-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Lightricks/LTX-2 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", 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") - Inference
- Notebooks
- Google Colab
- Kaggle
Unwanted text and subtitles are being generated together. I want to remove them.
Unwanted text and subtitles are being generated together. I want to remove them.
I'm speaking in Korean, but subtitles are being created with text that looks similar to Chinese.
Even when I include both the text and Chinese in the negative prompt, it's the same.
Is there a way to remove them?
μνμ§ μλ ν
μ€νΈμ μλ§μ΄ ν¨κ» μμ±λκ³ μμ΅λλ€. μ΄λ₯Ό μ κ±°νκ³ μΆμ΅λλ€.
νκ΅μ΄λ‘ λ§νκ³ μλλ°, μ€κ΅μ΄μ²λΌ 보μ΄λ ν
μ€νΈλ‘ μλ§μ΄ μμ±λ©λλ€.
ν
μ€νΈμ μ€κ΅μ΄λ₯Ό λͺ¨λ λΆμ ν둬ννΈμ ν¬ν¨μμΌλ λ§μ°¬κ°μ§μ
λλ€.
μ΄λ₯Ό μ κ±°ν λ°©λ²μ΄ μμκΉμ?
maybe it has a language barrier
try to write "subtitles" in the negative prompt
cfg 1 will ignore negative prompt i think
cfg 1 will ignore negative prompt i think
You can use the "LTXV NAG" node from https://github.com/kijai/ComfyUI-KJNodes, it allows for negative prompts with CFG 1