Video-to-Video
Diffusers
lora
template:diffusion-lora
ltx-2.3
colorize
black&white
color
video2video
vid2vid
IC-LoRA
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Lightricks/LTX-2.3", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("DoctorDiffusion/LTX-2.3-IC-LoRA-Colorizer")
prompt = "-"
image = pipe(prompt).images[0]LTX-2.3-IC-LoRA-Colorizer
- Prompt
- -
Model description
Still a work in progress.
Use with LTX-2.3 IC workflows to add color to black and white footage. It is not perfect by any means but for the best results I recommend to:
- Use the IC-LoRA workflow from Lightricks and bypass the controlnet part (I can provide a workflow if wanted)
- Prompt for what colors you want things to be
- Use a colorized inference frame for better color control
- Overlay the final result over your input using a "color" blend mode to preserve the fine details of the original footage.
- Generate color maps at half your target resolution for speed.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 406
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for DoctorDiffusion/LTX-2.3-IC-LoRA-Colorizer
Base model
Lightricks/LTX-2.3