ComfyUI Node: ClownGuide_StyleNorm_Advanced_HiDream

Authored by ClownsharkBatwing

Created

Updated

1222 stars

Run ClownGuide_StyleNorm_Advanced_HiDream without installing ComfyUI

This node already runs on ComfyICU. Open it in the browser, hit run, and you're billed for GPU seconds — not for setup, and not while you're idle.

Category

RES4LYF/sampler_extensions

Inputs

weight FLOAT
weight_scheduler
  • constant
  • simple
  • sgm_uniform
  • karras
  • exponential
  • ddim_uniform
  • beta
  • normal
  • linear_quadratic
  • kl_optimal
  • bong_tangent
  • beta57
double_blocks STRING
double_weights STRING
single_blocks STRING
single_weights STRING
mode
  • scattersort
  • AdaIN
noise_mode
  • direct
  • update
  • smart
  • recon
  • bonanza
ff_1 BOOLEAN
ff_1_silu BOOLEAN
ff_3 BOOLEAN
ff_13 BOOLEAN
ff_2 BOOLEAN
moe_gate BOOLEAN
topk_weight BOOLEAN
moe_ff_1 BOOLEAN
moe_ff_1_silu BOOLEAN
moe_ff_3 BOOLEAN
moe_ff_13 BOOLEAN
moe_ff_2 BOOLEAN
moe_sum BOOLEAN
moe_out BOOLEAN
double_img_io BOOLEAN
double_img_norm0 BOOLEAN
double_img_attn BOOLEAN
double_img_attn_gated BOOLEAN
double_img BOOLEAN
double_img_norm1 BOOLEAN
double_img_ff_i BOOLEAN
double_txt_io BOOLEAN
double_txt_norm0 BOOLEAN
double_txt_attn BOOLEAN
double_txt_attn_gated BOOLEAN
double_txt BOOLEAN
double_txt_norm1 BOOLEAN
double_txt_ff_t BOOLEAN
single_img_io BOOLEAN
single_img_norm0 BOOLEAN
single_img_attn BOOLEAN
single_img_attn_gated BOOLEAN
single_img BOOLEAN
single_img_norm1 BOOLEAN
single_img_ff_i BOOLEAN
attn_img_q_norm BOOLEAN
attn_img_k_norm BOOLEAN
attn_img_v_norm BOOLEAN
attn_txt_q_norm BOOLEAN
attn_txt_k_norm BOOLEAN
attn_txt_v_norm BOOLEAN
attn_img_double BOOLEAN
attn_txt_double BOOLEAN
attn_img_single BOOLEAN
proj_out BOOLEAN
start_step INT
end_step INT
invert_mask BOOLEAN
guide LATENT
mask MASK
weights SIGMAS
guides GUIDES

Outputs

GUIDES

Extension: RES4LYF

Advanced samplers with new noise scaling math to enable SDE sampling with all publicly available native models; new unsampling/noise inversion methods and other advanced img2img techniques for inpainting and/or guiding the sampling process with guide images, with results superior to FlowEdit, RF Inversion, and other SOTA implementations. Also new style transfer methods unique to this node pack; regional conditioning for HiDream, Flux, AuraFlow, and WAN; methods for eliminating Flux blur; and temporal conditioning (shift gradually from one prompt to the next with video). 115 sampler types, 24 noise types, 11 noise scaling modes, in a single node. Also includes a wide variety of QoF and other utility nodes for boosting detail, manipulating sigmas, latents, images, and more.

Authored by ClownsharkBatwing

Looking for a different node?

Run ClownGuide_StyleNorm_Advanced_HiDream without installing ComfyUI

This node already runs on ComfyICU. Open it in the browser, hit run, and you're billed for GPU seconds — not for setup, and not while you're idle.

Learn more