Text-to-Video
Diffusers
English
video-generation
ltx-video
ltx-2.3
omninft
image-to-video
generative-ai
diffusion
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("cnielsenla/LTX-2.3-22b_RL_Lora_Merge", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]LTX-2.3 OmniNFT RL Merged
This model is a merged checkpoint combining:
- :contentReference[oaicite:0]{index=0}
- :contentReference[oaicite:1]{index=1}
The LoRA weights from the OmniNFT RL release were merged directly into the base LTX-2.3 22B model to create a standalone merged .safetensors checkpoint.
Merge Details
Base model:
LTX-2.3 22B
Merged LoRA:
LTX-2.3-RL-Lora
Precision:
bf16
Notes
This repository contains a fully merged checkpoint intended for inference workflows that do not support external LoRA loading.
The merge was created using the official OmniNFT merge script.
Credits
Full credit goes to the original authors and teams behind:
- :contentReference[oaicite:2]{index=2}
- :contentReference[oaicite:3]{index=3}
Disclaimer
This is an unofficial merged checkpoint provided for research and experimentation purposes.
- Downloads last month
- 68
Model tree for cnielsenla/LTX-2.3-22b_RL_Lora_Merge
Base model
Lightricks/LTX-2.3