ComfyUI-Mana-Nodes

Required Inputs

font

To set the font and its styling you need to input 🆗 Font Properties node here.

canvas

To configure the canvas input the 🖼️ Canvas Properties

text

Specifies the text to be rendered on the images. Supports multiline text input for rendering on separate lines.

“`

“1”: “Hello”,

“10”: “World”,

“20”: “End”

“`

frame_count

Sets the amount of frames this node will output.

Optional Inputs

transcription

Input the transcription output from the 🎤 Speech Recognition node here.

Based on this transcription data, 🖼️ Canvas Properties and 🆗 Font Properties the text should be formatted in a way that builds up lines of words until there is no space on the canvas left (transcription_mode: fill, line).

highlight_font

Input a secondary font 🆗 Font Properties, that is used to highlight the active caption (transcription_mode: fill, line). When manually setting the text the following syntax can be used to defined which word/character:

Hello <tag>World</tag>

Outputs

images

The generated images with the specified text and configurations, in common ComfyUI format (compatible with other nodes).

transcription_framestamps

Framestamps formatted based on canvas, font and transcription settings.

Can be useful to manually correct errors by 🎤 Speech Recognition node.

Example: Save this output with 📝 Save/Preview Text -> manually correct mistakes -> remove transcription input from ✒️ Text to Image Generator node -> paste corrected framestamps into text input field of ✒️ Text to Image Generator node.

Required Inputs

font_file

Fonts located in the custom_nodes\ComfyUI-Mana-Nodes\font_files\example_font.ttf or system font directories (supports .ttf, .otf, .woff, .woff2).

font_size

Either set single value font_size or input animation definition via the ⏰ Scheduled Values node. (Convert font_size to input)

font_color

Either set single color value (CSS3/Color/Extended color keywords) or input animation definition via the 🌈 Preset Color Animations node. (Convert font_color to input)

x_offset, y_offset

Either set single horiontal and vertical offset value or input animation definition via the ⏰ Scheduled Values node. (Convert x_offset/y_offset to input)

rotation

Either set single rotation value or input animation definition via the ⏰ Scheduled Values node. (Convert rotation to input)

rotation_anchor_x, rotation_anchor_y

Horizontal and vertical offsets of the rotation anchor point, relative to the texts initial position.

kerning

Spacing between characters of font.

border_width

Width of the text border.

border_color

Either set single color value (CSS3/Color/Extended color keywords) or input animation definition via the 🌈 Preset Color Animations node. (Convert border_color to input)

shadow_color

Either set single color value (CSS3/Color/Extended color keywords) or input animation definition via the 🌈 Preset Color Animations node. (Convert shadow_color to input)

shadow_offset_x, shadow_offset_y

Horizontal and vertical offset of the text shadow.

Outputs

font

Used as input on ✒️ Text to Image Generator node for the font and highlight_font.

Required Inputs

height, width

Dimensions of the canvas.

background_color

Background color of the canvas. (CSS3/Color/Extended color keywords)

padding

Padding between image border and font.

line_spacing

Spacing between lines of text on the canvas.

Optional Inputs

images

Can be used to input images instead of using background_color.

Outputs

canvas

Used as input on ✒️ Text to Image Generator node to define the canvas settings.

Required Inputs

frame_count

Sets the range of the x axis of the chart. (always starts at 1)

value_range

Sets the range of the y axis of the chart. (Example: 25, will would be ranging from -25 to 25)

This can be changed by zooming via the mousewheel and will reset to the specified value if changed.

easing_type

Is used to generate values in between of the manually added values by the user by clicking the Generate Values button.

The available easing functions are:

step_mode

The option single will force the chart to display every single tick/step on the chart.

The option auto will automatically remove ticks/step to prevent overlapping.

animation_reset

Used to specify the reset behaviour of the animation.

scheduled_values

Adding Values: Click on the chart to add keyframes at specific points.

Editing Values: Double-click on a keyframe to edit its frame and value.

Deleting Values: Click on the delete button associated with each keyframe to remove it.

Generating Values: Click on the “Generate Values” button to interpolate values between existing keyframes.

Deleting Generated Values: Click on the “Delete Generated” button to remove all interpolated values.

Outputs

scheduled_values

Outputs a list of frame and value pairs and the animation_reset option.

At the moment this output can be used to animate the following widgets (Convert property to input) of the 🆗 Font Properties node:

Required Inputs

color_preset

Currently the following color animation presets are available:

animation_duration

Sets the length of the animation measured as frames.

animation_reset

Used to specify the reset behaviour of the animation.

Outputs

scheduled_colors

Outputs a list of frame and color definitions and the animation_reset option.

At the moment this output can be used to animate the following widgets (Convert property to input) of the 🆗 Font Properties node:

Converts spoken words in an audio file to text using a deep learning model.

Required Inputs

audio

Audio file path or URL.

wav2vec2_model

The Wav2Vec2 model used for speech recognition. (https://huggingface.co/models?search=wav2vec2)

spell_check_language

Language for the spell checker.

framestamps_max_chars

Maximum characters allowed until new framestamp line is created.

Optional Inputs

fps

Frames per second, used for synchronizing with video. (Default set to 30)

Outputs

transcription

Text transcription of the audio. (Should only be used as font2img transcription input)

raw_string

Raw string of the transcription without timestamps.

framestamps_string

Frame-stamped transcription.

timestamps_string

Transcription with timestamps.

Example Outputs

raw_string

Returns the transcribed text as one line.

THE GREATEST TRICK THE DEVIL EVER PULLED WAS CONVINCING THE WORLD HE DIDN'T EXIST

framestamps_string

Depending on the framestamps_max_chars parameter the sentece will be cleared and starts to build up again until max_chars is reached again.

"27": "THE",
"31": "THE GREATEST",
"43": "THE GREATEST TRICK",
"73": "THE GREATEST TRICK THE",
"77": "DEVIL",
"88": "DEVIL EVER",
"94": "DEVIL EVER PULLED",
"127": "DEVIL EVER PULLED WAS",
"133": "CONVINCING",
"150": "CONVINCING THE",
"154": "CONVINCING THE WORLD",
"167": "CONVINCING THE WORLD HE",
"171": "DIDN'T",
"178": "DIDN'T EXIST",

timestamps_string

Returns all transcribed words, their start_time and end_time in json format as a string.

[
  {
    "word": "THE",
    "start_time": 0.9,
    "end_time": 0.98
  },
  {
    "word": "GREATEST",
    "start_time": 1.04,
    "end_time": 1.36
  },
  {
    "word": "TRICK",
    "start_time": 1.44,
    "end_time": 1.68
  },
...
]

Required Inputs

video

Path the video file.

frame_limit

Maximum number of frames to extract from the video.

frame_start

Starting frame number for extraction.

filename_prefix

Prefix for naming the extracted audio file. (relative to .\ComfyUI\output)

Outputs

frames

Extracted frames as image tensors.

frame_count

Total number of frames extracted.

audio_file

Path of the extracted audio file.

fps

Frames per second of the video.

height, width:

Dimensions of the extracted frames.

Required Inputs

frames

Sequence of images to be used as video frames.

filename_prefix

Prefix for naming the video file. (relative to .\ComfyUI\output)

fps

Frames per second for the video.

Optional Inputs

audio_file

Audio file path or URL.

Outputs

video_file

Path to the created video file.

Converts text to speech and saves the output as an audio file.

Required Inputs

text

The text to be converted into speech.

filename_prefix

Prefix for naming the audio file. (relative to .\ComfyUI\output)

This node uses a text-to-speech pipeline to convert input text into spoken words, saving the result as a WAV file. The generated audio file is named using the provided filename prefix and is stored relative to the .\ComfyUI-Mana-Nodes directory.

Model: https://huggingface.co/spaces/suno/bark

Foreign Language

Bark supports various languages out-of-the-box and automatically determines language from input text. When prompted with code-switched text, Bark will even attempt to employ the native accent for the respective languages in the same voice.

Example:

Buenos días Miguel. Tu colega piensa que tu alemán es extremadamente malo. But I suppose your english isn't terrible.

Non-Speech Sounds

Below is a list of some known non-speech sounds, but we are finding more every day.

[laughter]
[laughs]
[sighs]
[music]
[gasps]
[clears throat]
— or … for hesitations
♪ for song lyrics
capitalization for emphasis of a word
MAN/WOMAN: for bias towards speaker

Example:

" [clears throat] Hello, my name is Suno. And, uh — and I like pizza. [laughs] But I also have other interests such as... ♪ singing ♪."

Music

Bark can generate all types of audio, and, in principle, doesn’t see a difference between speech and music. Sometimes Bark chooses to generate text as music, but you can help it out by adding music notes around your lyrics.

Example:

♪ In the jungle, the mighty jungle, the lion barks tonight ♪

Speaker Prompts

You can provide certain speaker prompts such as NARRATOR, MAN, WOMAN, etc. Please note that these are not always respected, especially if a conflicting audio history prompt is given.

Example:

WOMAN: I would like an oatmilk latte please.

MAN: Wow, that's expensive!

Required Inputs

string

The string to be written to the file.

filename_prefix

Prefix for naming the text file. (relative to .\output)