nodes/da2el-ai-D2-nodes-ComfyUI

Fork 0

Files

T

da2el-ai 8db69f53bb feat: Update documents

2024-11-23 06:51:44 +09:00

14 KiB

Raw Blame History

English | 日本語 | 繁体中文

Node

🍅 Sampler Nodes

D2 KSampler / D2 KSampler(Advanced)

KSampler that can input prompts as STRING

Input

cnet_stack
- For connecting to D2 Controlnet Loader
model / clip / vae / ..etc
- Same as standard KSampler
negative / positive
- Prompts in STRING format

Output

IMAGE
- Image output
positive / negative
- Input passthrough

🍅 Loader Node

D2 Checkpoint Loader

A Checkpoint Loader that outputs the full path of model files
Can automatically apply v_prediction settings when the filename contains "vpred"

Input

ckpt_name
- Checkpoint name
auto_vpred
- true: Automatically applies v_prediction settings if the filename contains "vpred"
sampling / zsnr
- Same settings as ModelSamplingDiscrete (details unknown)
multiplier
- Same settings as RescaleCFG (details unknown)

Output

model / clip / vae
- Same as the conventional CheckpointLoader.
ckpt_name / ckpt_hash / ckpt_fullpath
- Checkpoint name, hash, and full path.

D2 Controlnet Loader

Controlnet Loader that creates simple workflows when connected to D2 KSampler

Input

cnet_stack
- For connecting to D2 Controlnet Loader

Output

cnet_stack
- For connecting to D2 KSampler or D2 Controlnet Loader

🍅 Image Node

D2 Load Image

Load Image node that can extract prompts from images
Compatible with images created in StableDiffusion webui A1111 and NovelAI
Includes a button to open mask editor

Input

image_path
- Loads file when image path is input
- Used for connection with D2 Folder Image Queue

Output

IMAGE / MASK
- Image and mask
width / height
- Image size
positive / negative
- Prompts

Note: Prompts may not be retrievable depending on workflow configuration. For example, they cannot be retrieved without a node containing the string "KSampler" (e.g., Tiled KSampler).

D2 Load Folder Images

Batch loads and outputs images from a folder
Used with D2 Grid Image etc.
Use D2 Folder Image Queue for sequential processing

Input

folder
- Specify folder in full path
extension
- Specify like *.jpg to load only JPEG images
- Can also specify patterns like *silver*.webp

D2 Folder Image Queue

Outputs paths of images in a folder
Automatically executes Queue for the number of images when Queue is run

Input

folder
- Image folder
extension
- Specify file name filter
- *.*: All images
- *.png: PNG format only
start_at
- Image number to start processing
auto_queue
- true: Automatically execute remaining Queues
- false: Execute only once

Output

image_path
- Full path of image

D2 Grid Image

Outputs grid images
Supports both horizontal and vertical layouts

Input

max_columns
- Number of images to align horizontally
- Number of images vertically when swap_dimensions is true
grid_gap
- Gap between images
swap_dimensions
- true: Vertical direction
- false: Horizontal direction
trigger
- true: Output grid image
- false: Only retain images without outputting grid image

D2 Image Stack

Outputs multiple input images together
Can input up to 50 images

Input

image_count
- Can increase/decrease number of inputs. Maximum 50

D2 EmptyImage Alpha

Adds alpha channel (transparency) to EmptyImage

🍅 Size Node

D2 Get Image Size

Both outputs and displays size

D2 Size Selector

Node for selecting image size from presets
Can also get size from images
Rounding method can be selected from Ceil / Float / None

Input

images
- Used when getting size from images
- preset must be set to custom
preset
- Size presets
- Must be set to custom when using width height below or image sizes
- Edit /custom_nodes/D2-nodes-ComfyUI/config/sizeselector_config.yaml to modify presets
width / height
- Width/height dimensions
- preset must be set to custom
swap_dimensions
- Swap width/height
upscale_factor
- Value passed to other resize nodes. Does nothing in this node
prescale_factor
- Output width/height after resizing by this factor
round_method
- Round: Round to nearest
- Floor: Round down
- None: No rounding
batch_size
- Batch size to set for empty_latent

Output

width / height
- Input width, height multiplied by prescale_factor
upscale_factor / prescale_factor
- Passthrough of input
batch_size
- Passthrough of input
empty_latent
- Outputs latent created with specified size and batch size

D2 Image Resize

Simple image resizing
Precision up to 3 decimal places
Can select rounding, floor, or ceiling
Capable of upscaling using upscale models
Latent output is also possible (requires VAE)

D2 Resize Calculator

Can select rounding, floor, or ceiling

🍅 Text Node

D2 Regex Replace

Can replace using regular expressions
Multiple conditions can be specified
Supports reuse of regex match strings (e.g., \1, \2)
Target string can be specified by "tag unit" or "whole"

Input

text
- Target string for search
mode
- Tag: Break down text by newlines and "," and replace individually
- Advanced: Replace text as a whole
regex_and_output
- List of search strings and output strings
- Write in following format
- If output string is empty, matched part is deleted
- No limit on number of entries

Search string 1
--
Output string 1
--
Search string 2
--
Output string 2

Output

text
- Text after replacement

Sample

Sample for removing Pony series quality tags.

Mode: Tag

Input text

score_9, score_8_up, (score_7_up, score_6_up:0.8) , rating_explicit, source_anime, BREAK
1girl, swimsuit

Regex Replace

.*(score_|rating_|source_).*
--
--
BREAK
--

Output text

1girl, swimsuit

D2 Regex Switcher

Searches input text with regex and outputs matching text
Main purpose is switching quality tags per Checkpoint
When matching string is found in input text, outputs target string and match index (starting from 0)
Can concatenate strings at front and back

Input

text
- Search target string
prefix
- String to concatenate at front
suffix
- String to concatenate at back
regex_and_output
- List of search strings and output strings
- Write in following format
pre_delim
- Character inserted between prefix and regex_and_output
- Comma: , / Line break: newline / None: nothing
suf_delim
- Character inserted between regex_and_output and suffix

Output

combined_text
- String combining prefix + output string + suffix
prefix / suffix
- Input passthrough

D2 Multi Output

Node that outputs generic parameters like seed and cfg as lists

Input

type
- FLOAT: Floating point numbers. For CFG etc.
- INT: Integers. For steps etc.
- STRING: Strings. For sampler etc.
- SEED: Can input seed values with random number button
Add Random
- Adds random numbers to input field
- Only shown when type is SEED

🍅 XY Plot Node

D2 XY Plot

Node for creating versatile XY Plot workflows
X/Y inputs are simple newline-separated text for easy combination with other nodes

Input

x_type / y_type
- Specify data type of x_list y_list from STRING INT FLOAT
x_title / y_title
- Text to add to header text
x_list / y_list
- XY Plot change contents
- Newline-separated text that can be input using other nodes
auto_queue
- true: Automatically execute required number of Queues
- false: Manually execute Queue
Reset index
- Reset index with this button when stopped midway

Output

X / Y
- Elements retrieved from x_list y_list
x_annotation / y_annotation
- Header text to connect to D2 XY Grid Image
status
- Control signal to connect to D2 XY Grid Image
index
- Current processing count

D2 XY Grid Image

Grid image creation node used with D2 XY Plot

Input

x_annotation / y_annotation
- Header text for grid image
status
- Control text from D2 XY Plot
- INIT: Initialize
- FINISH: Output grid image
- {empty string}: Other states
font_size
- Header text font size
grid_gap
- Gap between images
swap_dimensions
- true: Vertical grid
- false: Horizontal grid
grid_only
- true: Output only grid image
- false: Output individual images too

D2 XY Prompt SR

Search and replace input text to pass to D2 XY Plot
Can output as list

Input

prompt
- Prompt. Can include newlines
search_txt
- Search target text. Can include multiple words
- Cannot use newlines
replace
- Replacement text
- OK to include "," as it's separated by newlines

Output

x / y_list
- Connect to D2 XY Plot
LIST
- Output replaced text as list

D2 XY Prompt SR2

Search and replace prompts received from D2 XY Plot before passing to KSampler
Use this to recreate Stable Diffusion webui A1111's Prompt S/R

Input

x_y
- Replacement text received from D2 XY Plot
prompt
- Target text for replacement
search
- Search text. Can include multiple words
- Cannot use newlines

D2 XY Seed

Outputs random number when -1 is specified
Other numbers are output as-is
Must set x/y_type to INT on D2 XY Plot side

D2 XY Checkpoint List / D2 XY Lora List

Node to pass Checkpoint/Lora to D2 XY Plot
Can specify up to 50

D2 XY Model List

A node that passes Checkpoint / Lora lists to D2 XY Plot
Useful when you want to get a large list of models but find it tedious to select them one by one in D2 Checkpoint List
Click get_list to retrieve the model list, then edit it to keep only the ones you need

D2 XY Folder Images

Node to pass image paths from specified folder to D2 XY Plot

D2 XY Annotation

Used to add headers when not using D2 XY Plot or when doing special XY Plot

D2 XY List To Plot

Converts output from list-outputting nodes for use with D2 XY Plot
Internally just does "\n".join(list), so will behave unexpectedly if list contents contain newlines

🍅 Refiner Node

D2 Refiner Steps

Node for outputting steps for Refiner

Input

steps
- Total step count
start
- Starting steps for first KSampler
end
- Ending steps for first KSampler

Output

steps / start / end
- Input passthrough
refiner_start
- Starting steps for second KSampler

D2 Refiner Steps A1111

Node that can specify denoise for Refiner in img2img

Input

steps
- Total step count
denoise
- Specify denoise for img2img
switch_at
- What percentage of total steps to switch to next KSampler

Output

steps
- Input passthrough
start
- Starting steps for first KSampler
end
- Ending steps for first KSampler
refiner_start
- Starting steps for second KSampler

D2 Refiner Steps Tester

Node for checking steps

🍅 Float Palet

D2 Queue Button

Button to generate specified number of images (Batch count)
Can be moved by dragging left edge of palette

Configure visibility in ComfyUI settings under D2 category
Number of images can also be set from settings screen
Separate numbers with comma (,)

Prompt convert dialog

Dialog for converting weights between NovelAI and StableDiffusion
Open from Prompt convert button
Hidden by default
Enable display by activating settings > D2 > Show prompt convert button

14 KiB Raw Blame History

Node

🍅 Sampler Nodes

D2 KSampler / D2 KSampler(Advanced)

Input

Output

🍅 Loader Node

D2 Checkpoint Loader

Input

Output

D2 Controlnet Loader

Input

Output

🍅 Image Node

D2 Load Image

Input

Output

D2 Load Folder Images

Input

D2 Folder Image Queue

Input

Output

D2 Grid Image

Input

D2 Image Stack

Input

D2 EmptyImage Alpha

🍅 Size Node

D2 Get Image Size

D2 Size Selector

Input

Output

D2 Image Resize

D2 Resize Calculator

🍅 Text Node

D2 Regex Replace

Input

Output

Sample

D2 Regex Switcher

Input

Output

D2 Multi Output

Input

🍅 XY Plot Node

D2 XY Plot

Input

Output

D2 XY Grid Image

Input

D2 XY Prompt SR

Input

Output

D2 XY Prompt SR2

Input

D2 XY Seed

D2 XY Checkpoint List / D2 XY Lora List

D2 XY Model List

D2 XY Folder Images

D2 XY Annotation

D2 XY List To Plot

🍅 Refiner Node

D2 Refiner Steps

Input

Output

D2 Refiner Steps A1111

Input

Output

D2 Refiner Steps Tester

🍅 Float Palet

D2 Queue Button

Prompt convert dialog

14 KiB

Raw Blame History