import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Lightricks/LTX-Video", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("systms/SYSTMS-FLW-IC-LORA-LTX-2.3")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]
SYSTMS / FLW · v1.0
/FLW
LTX 2.3 IC-LoRA for seamless shot-to-shot transitions.
↓ LoRA ↓ Workflow ↗ Comfy Cloud
──
02 LOOPS · LTX-VIDEO + FLW
── PARAMETERS
LTX 2.3 + FLW
Trigger word
FLWLoRA strength
1.0Control method
Insert 50% gray frames (
RGB 127, 127, 127) between the clips you want to transition between. No mask needed.
── PROMPTING FORMULA
REPLACE THE BRACKETS
FLW, [Action A] seamlessly transforms into [Action B],
[Subject A description] becomes [Subject B description],
[Setting A] shifts to [Setting B],
[Camera behavior across the transition],
[Lighting/mood continuity]
BUILT BY SYSTMS · 2026
APACHE 2.0
- Downloads last month
- 849
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for systms/SYSTMS-FLW-IC-LORA-LTX-2.3
Base model
Lightricks/LTX-Video