ComfyUI Node: π Kraken KSampler
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
π¦ Kraken Tools/Sampling
Inputs
- 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
- simple
- sgm_uniform
- karras
- exponential
- ddim_uniform
- beta
- normal
- linear_quadratic
- kl_optimal
- enable
- disable
- disable
- enable
- auto
- use
- ignore
- auto
- on
- off
- off
- on
- off
- on
- off
- on
Outputs
LATENT
IMAGE
Extension: Kraken Tools
15 productivity nodes: Kraken Unbound Prompt (vision-enabled prompt builder with Qwen2-VL), WAN Prompt Splitter (cinematic styling), Ollama Prompt Chat (LLM enhancement), LoRA Loader with CivitAI trigger fetching, Dual CLIP Loader (Flux/SD3/SDXL), smart KSampler (AMP handling for WAN/Flow/FP8), Empty Latent with aspect presets, Upscale & Tile Calculator for Ultimate SD Upscale, Resolution Helper, Image Processor, WAN Helper, and more.
Authored by krakenunbound
Looking for a different node?
More nodes in Kraken Tools
- π Kraken Checkpoint Loader
- π Kraken Dual CLIP Loader
- π Kraken Empty Latent Image
- π Kraken Image Processor
- π Kraken Image Resize
- π Kraken Last Frame + Meta
- π Kraken LoRA Loader (3)
- π Kraken Ollama Prompt Chat
- π Kraken Preset From Image
- π Kraken Resolution Helper
- π Kraken Unbound Prompt
- π Kraken Upscale & Tile Calc
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.