ComfyUI Node: LTX2 Efficient Video Sampler
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.
Category
video/ltx2
Inputs
model MODEL
latent_video LATENT
positive CONDITIONING
negative CONDITIONING
seed INT
steps INT
cfg FLOAT
sampler_name
- euler
- euler_cfg_pp
- euler_ancestral
- euler_ancestral_cfg_pp
- heun
- heunpp2
- exp_heun_2_x0
- exp_heun_2_x0_sde
- dpm_2
- dpm_2_ancestral
- lms
- dpm_fast
- dpm_adaptive
- dpmpp_2s_ancestral
- dpmpp_2s_ancestral_cfg_pp
- dpmpp_sde
- dpmpp_sde_gpu
- dpmpp_2m
- dpmpp_2m_cfg_pp
- dpmpp_2m_sde
- dpmpp_2m_sde_gpu
- dpmpp_2m_sde_heun
- dpmpp_2m_sde_heun_gpu
- dpmpp_3m_sde
- dpmpp_3m_sde_gpu
- ddpm
- lcm
- ipndm
- ipndm_v
- deis
- res_multistep
- res_multistep_cfg_pp
- res_multistep_ancestral
- res_multistep_ancestral_cfg_pp
- gradient_estimation
- gradient_estimation_cfg_pp
- er_sde
- seeds_2
- seeds_3
- sa_solver
- sa_solver_pece
- ddim
- uni_pc
- uni_pc_bh2
denoise FLOAT
optimization_preset
- Quality - Fast (RTX 3080+)
- Quality - Balanced (RTX 3060/3070)
- Quality - RTX 2060 6GB
- Quality - Cool (RTX 2060 6GB)
- Quality - Ultra Cool (Low Power GPUs)
- Thermal Auto-Scale
- Custom
target_temp INT
frame_stride INT
attention_window INT
freeze_ratio FLOAT
thermal_throttle BOOLEAN
interpolation_method
- linear
- slerp
- motion
- none
optimization_engine
- None
- Adaptive Cache (2-4x speedup)
- Token Merge / VidToMe (1.3-1.5x)
- Step Adaptive (1.2-1.4x)
- Combined (2-5x speedup)
engine_cache_ratio FLOAT
engine_merge_ratio FLOAT
context_slice_method
- Keep Last 4096 (Slot 2 - LTX Connector)
- Keep First 4096 (Slot 1 - T5)
- Auto-detect
sigmas SIGMAS
max_shift FLOAT
base_shift FLOAT
terminal FLOAT
stretch BOOLEAN
frame_rate FLOAT
Outputs
LATENT
Extension: comfyui-ltx2-efficient
High-performance custom node for LTX2 video generation designed to reduce GPU usage, VRAM requirements, and temperature on consumer GPUs.
Authored by kakachiex2
Looking for a different node?
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.