EasyUse/Pipegenerated

Pipe Edit(pipeEdit)

Pipe Edit is an all-in-one pipeline editing node for EasyUse pipes.

pipe Edit

pipe
model
pos
neg
latent
vae
clip
image
pipe
model
pos
neg
latent
vae
clip
image
clip_skip
-1
optional_positive
STRING
positive_token_normalization
COMBO
positive_weight_interpretation
COMBO
optional_negative
STRING
negative_token_normalization
COMBO
negative_weight_interpretation
COMBO
a1111_prompt_style
conditioning_mode
replace
average_strength
1.00
old_cond_start
0.000
old_cond_end
1.000
new_cond_start
0.000
new_cond_end
1.000
Easy Use

Description

Pipe Edit is an all-in-one pipeline editing node for EasyUse pipes. It accepts a PIPE_LINE and optional direct component inputs, lets you edit the positive/negative conditioning, CLIP skip, and other pipe fields, and returns both an updated PIPE_LINE and each component separately. This saves you from manually unpacking and repacking the pipe when you only need to change one or two values.

When optional_positive or optional_negative is filled in, the node re-encodes that prompt with the active CLIP model and combines it with the existing conditioning using the selected conditioning_mode. The advanced prompt controls let you match the token normalization and weight interpretation of the prompt syntax you are using.

Inputs

InputTypeDefaultDescription
clip_skipINT-1Number of CLIP layers to skip, counting from the end as a negative value. -1 is the typical value used by many models. Range: -24 to 0.
optional_positiveSTRING""Optional positive prompt. Leave empty to keep the existing positive conditioning. When provided, it is encoded with CLIP and combined with pos according to conditioning_mode.
positive_token_normalizationCOMBOToken normalization for the positive prompt. Options: none, mean, length, length+mean.
positive_weight_interpretationCOMBOWeight interpretation syntax for the positive prompt. Options: comfy, A1111, comfy++, compel, fixed attention.
optional_negativeSTRING""Optional negative prompt. Leave empty to keep the existing negative conditioning. When provided, it is encoded with CLIP and combined with neg according to conditioning_mode.
negative_token_normalizationCOMBOToken normalization for the negative prompt. Options: none, mean, length, length+mean.
negative_weight_interpretationCOMBOWeight interpretation syntax for the negative prompt. Options: comfy, A1111, comfy++, compel, fixed attention.
a1111_prompt_styleBOOLEANfalseEnables Automatic1111-style prompt processing. Use this when copying prompts written for A1111-based UIs.
conditioning_modeCOMBOreplaceDetermines how newly encoded prompt conditioning is combined with the existing conditioning. Options: replace, concat, combine, average, timestep.
average_strengthFLOAT1.0Blending strength used when conditioning_mode is average. 0.0 keeps the original conditioning only; 1.0 keeps the new conditioning only. Range: 0.0 to 1.0.
old_cond_startFLOAT0.0Timestep fraction at which the original conditioning becomes active when conditioning_mode is timestep. 0.0 represents the first denoising step.
old_cond_endFLOAT1.0Timestep fraction at which the original conditioning stops being active when conditioning_mode is timestep. 1.0 represents the final denoising step.
new_cond_startFLOAT0.0Timestep fraction at which the newly encoded conditioning becomes active when conditioning_mode is timestep.
new_cond_endFLOAT1.0Timestep fraction at which the newly encoded conditioning stops being active when conditioning_mode is timestep.
pipePIPE_LINEExisting pipeline to edit. Supplies default values for model, pos, neg, latent, vae, clip, and image when the corresponding direct inputs are not connected.
modelMODELDirect model input. Overrides the model from pipe.
posCONDITIONINGDirect positive conditioning input. Overrides the positive conditioning from pipe.
negCONDITIONINGDirect negative conditioning input. Overrides the negative conditioning from pipe.
latentLATENTDirect latent input. Overrides the latent from pipe.
vaeVAEDirect VAE input. Overrides the VAE from pipe.
clipCLIPDirect CLIP model input. Overrides the CLIP from pipe.
imageIMAGEDirect image input. Overrides the image from pipe.

Outputs

OutputTypeDescription
pipePIPE_LINEUpdated pipeline containing all edited components.
modelMODELThe model from the pipe or direct model input.
posCONDITIONINGPositive conditioning after prompt editing.
negCONDITIONINGNegative conditioning after prompt editing.
latentLATENTThe latent from the pipe or direct latent input.
vaeVAEThe VAE from the pipe or direct vae input.
clipCLIPThe CLIP model with clip_skip applied.
imageIMAGEThe image from the pipe or direct image input.

Usage Notes

  • Connect a pipe to edit an existing pipeline. Any of the optional component inputs can be connected to override the corresponding value; if an input is not connected, the value passes through from the pipe unchanged.
  • The node also works without a pipe if you connect the components directly. In that case, the outputs mirror the connected inputs and the output pipe bundles them into a new PIPE_LINE.
  • clip_skip only affects the output CLIP model. To apply a new CLIP skip to conditioning, re-encode the prompt by filling in optional_positive and/or optional_negative; the active CLIP is used for that re-encoding.
  • When both prompt fields are left empty, no prompt re-encoding is performed and the original pos/neg conditioning passes through, apart from modifications implied by modes such as timestep.
  • The conditioning_mode controls how newly encoded prompt conditioning relates to the existing conditioning:
    • replace: Uses the new conditioning instead of the original.
    • concat: Appends the new conditioning to the original.
    • combine: Merges the new and original conditioning.
    • average: Blends them according to average_strength.
    • timestep: Uses old_cond_start/old_cond_end and new_cond_start/new_cond_end to schedule when each conditioning is active during denoising.
  • In timestep mode, start and end values are fractions of the denoising process: 0.0 is the first/noisy step and 1.0 is the last/clean step. The default ranges of 0.0 to 1.0 keep each conditioning active for the entire process.

Comments

Sign in with GitHub to join the discussion.

Loading comments…