ComfyUI Node: Checkpoint & Sampler for DualCLIP
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
ZSQ/Loaders
Inputs
ckpt_name
clip_name1
clip_name2
types
- sdxl
- sd3
- flux
resolution
- width x height
- 128 x 128
- 256 x 256
- 512 x 512
- 512 x 768
- 576 x 1024
- 768 x 512
- 768 x 768
- 768 x 1024
- 768 x 1280
- 768 x 1344
- 768 x 1536
- 816 x 1920
- 832 x 1152
- 832 x 1216
- 896 x 1152
- 896 x 1088
- 1024 x 1024
- 1024 x 576
- 1024 x 768
- 1080 x 1920
- 1440 x 2560
- 1088 x 896
- 1216 x 832
- 1152 x 832
- 1152 x 896
- 1280 x 768
- 1344 x 768
- 1536 x 640
- 1536 x 768
- 1920 x 816
- 1920 x 1080
- 2560 x 1440
positive_text STRING
negative_text STRING
batch_size INT
steps INT
cfg FLOAT
seed INT
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
scheduler
- simple
- sgm_uniform
- karras
- exponential
- ddim_uniform
- beta
- normal
- linear_quadratic
- kl_optimal
denoise FLOAT
optional_lora_stack ZSQ_LORA_STACK
optional_controlnet_stack ZSQ_CONTROL_NET_STACK
Outputs
IMAGE
Extension: zsq_prompt
NODES: PromptStyler, PromptLatent, PromptCLIPEncode, PromptSelector
Authored by windfancy
Looking for a different node?
More nodes in zsq_prompt
Other ZSQ/Loaders nodes
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.