LTX2.3_transformer_only_comfy
1
—
by
Bedovyy
Other
OTHER
2.3B params
New
0 downloads
Early-stage
Edge AI:
Mobile
Laptop
Server
6GB+ RAM
Mobile
Laptop
Server
Quick Summary
AI model with specialized capabilities.
Device Compatibility
Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
3GB+ RAM
Code Examples
pythonpytorch
import sys
from safetensors import safe_open
from safetensors.torch import save_file
import torch
def main():
src1_path, src2_path, output_path = sys.argv[1:4]
out_tensors = {}
with safe_open(src1_path, framework="pt") as f1:
for k in f1.keys():
out_tensors[k] = f1.get_tensor(k)
metadata = f1.metadata() or {}
with safe_open(src2_path, framework="pt") as f2:
for k in f2.keys():
if k.endswith(".input_scale"):
base_key = k.replace(".input_scale", "")
if f2.get_tensor(f"{base_key}.comfy_quant") is not None:
out_tensors[k] = f2.get_tensor(k)
save_file(out_tensors, output_path, metadata=metadata)
if __name__ == "__main__":
main()Deploy This Model
Production-ready deployment in minutes
Together.ai
Instant API access to this model
Production-ready inference API. Start free, scale to millions.
Try Free APIReplicate
One-click model deployment
Run models in the cloud with simple API. No DevOps required.
Deploy NowDisclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.