Video-to-Video
Diffusers
English
video-editing
video-restoration
ltx-video
ltx-2-3
dit
ic-lora
watermark-removal
subtitle-removal
super-resolution
hd-enhancement
joyfox
Instructions to use joyfox/LTX2.3-ICEdit-Insight with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use joyfox/LTX2.3-ICEdit-Insight with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("joyfox/LTX2.3-ICEdit-Insight", torch_dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
ltx2.3-ic-watermark-remove-general.safetensors does not remove Gemini logo well
#5
by harsh9838 - opened
Hi, thanks for releasing LTX2.3-ICEdit-Insight.
I found that ltx2.3-ic-watermark-remove-general.safetensors does not work well on the Gemini logo use case. In my tests, the Gemini logo is often only partially removed, remains visibly recognizable, or leaves obvious artifacts after editing.
Could you please retrain or extend the watermark/logo removal coverage to include this case? It would be especially helpful if the training data included:
- Gemini wordmark/logo variants
- Different sizes and placements
- Light/dark backgrounds
- Semi-transparent overlays
- Low-resolution / compressed video frames
This seems like an important real-world logo-removal case that the current weights do not generalize well to.
Thanks!