Skip to content

docs: sync built-in nodes documentation (weekly update) #1340

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
comfyui-wiki merged 2 commits into from
Aug 3, 2026
Merged

docs: sync built-in nodes documentation (weekly update) #1340

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
d4f9e77
Weekly node docs sync 2026-08-02
lin-bot23 Aug 1, 2026
c9ef422
docs: normalize ja Required column to はい/いいえ (consistency with siblin…
lin-bot23 Aug 1, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions built-in-nodes/AnimaLLLiteApply.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,13 +14,13 @@ AnimaLLLiteApply applies a lightweight animation patch to a diffusion model, ena
|-----------|-------------|-----------|----------|-------|
| `model` | The base diffusion model to apply the patch to | MODEL | Yes | |
| `model_patch` | The pre-configured animation patch to apply | MODEL_PATCH | Yes | |
| `image` | The reference image to guide the generation | IMAGE | Yes | |
| `image` | The reference image to guide the generation. Only the first 3 color channels (RGB) are used | IMAGE | Yes | |
| `strength` | The strength of the patch effect (default: 1.0) | FLOAT | Yes | -10.0 to 10.0 |
| `start_percent` | The percentage of the denoising process at which the patch starts taking effect (default: 0.0) | FLOAT | Yes | 0.0 to 1.0 |
| `end_percent` | The percentage of the denoising process at which the patch stops taking effect (default: 1.0) | FLOAT | Yes | 0.0 to 1.0 |
| `mask` | An optional mask to limit the patch effect to specific areas of the image | MASK | No | |

**Note on parameter constraints:** If the `model_patch` has 4 input channels and no `mask` is provided, a zero mask is automatically created to match the image dimensions. If the `model_patch` does not have 4 input channels, the `mask` parameter is ignored and set to `None`.
**Note on parameter constraints:** If the `model_patch` has 4 input channels and no `mask` is provided, a zero mask is automatically created to match the image dimensions. If the `model_patch` does not have 4 input channels, the `mask` parameter is ignored and set to `None`. This node is marked as experimental in ComfyUI.

## Outputs

Expand Down
8 changes: 5 additions & 3 deletions built-in-nodes/BerniniConditioning.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@ icon: "circle"
mode: wide
---

The BerniniConditioning node prepares video and image conditioning data for the Wan2.2-A14B model. It encodes source videos, reference videos, and reference images using the provided VAE, then attaches them to the conditioning data for in-context generation tasks. The task is automatically inferred from which inputs are connected.
The BerniniConditioning node prepares video and image conditioning data for the Wan2.2-A14B model. It encodes source videos, reference videos, and reference images using the provided VAE, then attaches them to the conditioning data as in-context tokens. The task is automatically inferred from which inputs are connected.

## Inputs

Expand All @@ -20,8 +20,8 @@ The BerniniConditioning node prepares video and image conditioning data for the
| `length` | Number of frames in the output latent (default: 81) | INT | Yes | 1 to 8192 (step: 4) |
| `batch_size` | Number of videos to generate in a single batch (default: 1) | INT | Yes | 1 to 4096 |
| `source_video` | Source video to edit or restyle (v2v, rv2v). Resized to width/height and trimmed to length. | IMAGE | No | - |
| `reference_video` | Video to insert into the source video (ads2v). | IMAGE | No | - |
| `reference_images` | Reference images injected as in-context tokens (r2v, rv2v). Up to 8 images can be provided. | IMAGE | No | 0 to 8 images |
| `reference_video` | Video to insert into the source video (ads2v). Trimmed to length and resized with preserved aspect ratio (long edge capped at ref_max_size). | IMAGE | No | - |
| `reference_images` | Reference images injected as in-context tokens (r2v, rv2v). Each image is encoded independently at its own native aspect ratio (long edge capped at ref_max_size). Up to 8 images can be provided. | IMAGE | No | 0 to 8 images |
| `ref_max_size` | Max size for the long edge of reference_video and reference_images. Resized with preserved aspect ratio and snapped to 16px (default: 848). | INT | No | 16 to 8192 (step: 16) |

**Note:** The task is inferred from which inputs are connected:
Expand All @@ -31,6 +31,8 @@ The BerniniConditioning node prepares video and image conditioning data for the
- `reference_images` only → reference-to-video (r2v)
- `source_video` + `reference_video` → insert image/video into video (ads2v)

Context streams are attached in a fixed order: `source_video` (source ID 1), then `reference_video` (source ID 2), then each reference image (source IDs 3, 4, ...). A reference image input containing multiple images contributes one stream per image.

## Outputs

| Output Name | Description | Data Type |
Expand Down
10 changes: 5 additions & 5 deletions built-in-nodes/BuildJsonPromptIdeogram.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,14 +13,14 @@ This node constructs a structured JSON prompt specifically formatted for the Ide
| Parameter | Description | Data Type | Required | Range |
|-----------|-------------|-----------|----------|-------|
| `element` | Prompt elements from the node Create Bounding Boxes. | ARRAY | Yes | - |
| `high_level_description` | Optional description of the image in one or two sentences. Strongly recommended for better results. (default: empty) | STRING | No | - |
| `background` | Description of the image background or environment. Providing a value is strongly recommended – the node will run with an empty string but results may be unpredictable. (default: empty) | STRING | No | - |
| `high_level_description` | Optional description of the image in one or two sentences. Strongly recommended. (default: empty) | STRING | No | - |
| `background` | Mandatory description of the image background or environment. Providing a value is strongly recommended – the node will run with an empty string but results may be unpredictable. (default: empty) | STRING | No | - |

@coderabbitai coderabbitai Bot Aug 1, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

📐 Maintainability & Code Quality | 🟡 Minor | ⚡ Quick win

Split the dash-joined clauses into two sentences.

The background description joins two independent clauses with a dash. Write: Providing a value is strongly recommended. The node will run with an empty string, but results may be unpredictable. No dash, less clash.

As per coding guidelines: In English MDX, prefer short, direct sentences over stacked clauses joined by dashes.

🤖 Prompt for AI Agents 
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@built-in-nodes/BuildJsonPromptIdeogram.mdx` at line 17, Update the
`background` row description in the node documentation to replace the
dash-joined clauses with two direct sentences: state that providing a value is
strongly recommended, then explain that an empty string still runs but may
produce unpredictable results.

Source: Coding guidelines

| `style` | The visual style category for the generated image. Select one of the options. (default: "none") | COMBO | Yes | `"none"`<br />`"photo"`<br />`"art_style"` |
| `photo` | Camera or lens details for photographic outputs (e.g. 35mm, f/1.4, bokeh). Only available when `style` is set to "photo". (default: empty) | STRING | No | - |
| `art_style` | Art style description (e.g. flat vector illustration, bold outlines). Only available when `style` is set to "art_style". (default: empty) | STRING | No | - |
| `aesthetics` | Aesthetic keywords (e.g. moody, cinematic, desaturated). Providing a value is strongly recommended. (default: empty) | STRING | No | - |
| `lighting` | Lighting description (e.g. golden hour, rim light, dramatic shadows). Providing a value is strongly recommended. (default: empty) | STRING | No | - |
| `medium` | Medium type (e.g. photograph, illustration, 3d_render, painting, graphic_design). Providing a value is strongly recommended. (default: empty) | STRING | No | - |
| `aesthetics` | Mandatory aesthetic keywords (e.g. moody, cinematic, desaturated). Providing a value is strongly recommended. (default: empty) | STRING | No | - |
| `lighting` | Mandatory lighting description (e.g. golden hour, rim light, dramatic shadows). Providing a value is strongly recommended. (default: empty) | STRING | No | - |
| `medium` | Mandatory medium type (e.g. photograph, illustration, 3d_render, painting, graphic_design). When style = photo, set to photograph. Providing a value is strongly recommended. (default: empty) | STRING | No | - |
Comment on lines +17 to +23

@coderabbitai coderabbitai Bot Aug 1, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🗄️ Data Integrity & Integration | 🟡 Minor | ⚡ Quick win

Resolve the contradictory requiredness guidance.

The table marks background, aesthetics, lighting, and medium as Required: No, but their descriptions call them “Mandatory”. The note also says empty strings are allowed. Use one term consistently. If empty values are valid, use “Recommended for reliable generation”. If the node enforces these values, mark them as required and document the validation.

🤖 Prompt for AI Agents 
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@built-in-nodes/BuildJsonPromptIdeogram.mdx` around lines 17 - 23, Update the
descriptions for background, aesthetics, lighting, and medium in the parameter
table to say “Recommended for reliable generation” instead of “Mandatory,”
preserving their current optional status and empty-string defaults.

| `color_palette` | Hex color codes that steer the image's dominant colors. Up to 16 entries. | COLORS | No | - |

**Note:** When `style` is set to "photo", the `photo` input becomes available and you should usually set `medium` to "photograph". When `style` is set to "art_style", the `art_style` input becomes available. The `background`, `aesthetics`, `lighting`, and `medium` parameters have default empty strings but are considered mandatory for reliable image generation; providing values is strongly recommended.
Expand Down
28 changes: 14 additions & 14 deletions built-in-nodes/ByteDanceSeedAudio.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,33 +12,33 @@ Generate speech, music, sound effects and multi-speaker dialogue from a single p

| Parameter | Description | Data Type | Required | Range |
|-----------|-------------|-----------|----------|-------|
| `text_prompt` | Describe the voice(s), emotion, pacing, ambience, background music and sound effects, and include the lines to speak (name characters inline for dialogue). In 'audio reference' mode, refer to connected clips by order as @Audio1, @Audio2, @Audio3. Maximum 3000 characters. | STRING | Yes | 1 to 3000 characters |
| `reference_mode` | How to condition the voice: 'text only' (describe everything in the prompt), 'audio reference' (clone up to 3 voices, tagged @Audio1-3), 'image reference' (derive a voice from one character image), or 'preset voice' (pick a built-in named voice that reads the prompt). | COMBO | Yes | `"text only"`<br />`"audio reference"`<br />`"image reference"`<br />`"preset voice"` |
| `reference_audio_1` | Reference clip for voice cloning, tagged @Audio1 in the prompt. Up to 30s. Only available when `reference_mode` is "audio reference". | AUDIO | No | Up to 30 seconds |
| `reference_audio_2` | Reference clip tagged @Audio2 in the prompt. Up to 30s. Only available when `reference_mode` is "audio reference". | AUDIO | No | Up to 30 seconds |
| `reference_audio_3` | Reference clip tagged @Audio3 in the prompt. Up to 30s. Only available when `reference_mode` is "audio reference". | AUDIO | No | Up to 30 seconds |
| `reference_image` | A single character image; the model derives a voice from it. Cannot be combined with reference audio. Only available when `reference_mode` is "image reference". | IMAGE | No | - |
| `preset_voice` | A built-in TTS 2.0 voice that reads the prompt. No reference clip needed, and @AudioN tags are not used in this mode. Only available when `reference_mode` is "preset voice". | COMBO | No | Multiple options available (see description) |
| `text_prompt` | Describe the voice(s), emotion, pacing, ambience, background music and sound effects, and include the lines to speak (name characters inline for dialogue). In "audio reference" mode, refer to connected clips by order as @Audio1, @Audio2, @Audio3. With the multilingual model, a quoted line can start with a timestamp range that controls when and how long it is spoken, e.g. `[5.5s:8.0s] Wait for me!`. Write the prompt in the same language as the lines to speak. Minimum 1 character, maximum 3000 characters. | STRING | Yes | 1 to 3000 characters |
| `reference_mode` | How to condition the voice: "text only" (describe everything in the prompt), "audio reference" (clone up to 3 voices, tagged @Audio1-3), "image reference" (derive a voice from one character image), or "preset voice" (pick a built-in named voice that reads the prompt). | COMBO | Yes | `"text only"`<br />`"audio reference"`<br />`"image reference"`<br />`"preset voice"` |
| `reference_audio_1` | Reference clip for voice cloning, tagged @Audio1 in the prompt. Up to 30s. Available only when `reference_mode` is "audio reference". | AUDIO | No | Up to 30 seconds |
| `reference_audio_2` | Reference clip tagged @Audio2 in the prompt. Up to 30s. Available only when `reference_mode` is "audio reference". | AUDIO | No | Up to 30 seconds |
| `reference_audio_3` | Reference clip tagged @Audio3 in the prompt. Up to 30s. Available only when `reference_mode` is "audio reference". | AUDIO | No | Up to 30 seconds |
| `reference_image` | A single character image; the model derives a voice from it. Cannot be combined with reference audio. Available only when `reference_mode` is "image reference". | IMAGE | No | - |
| `preset_voice` | A built-in TTS 2.0 voice that reads the prompt. No reference clip needed, and @AudioN tags are not used in this mode. Required when `reference_mode` is "preset voice". | COMBO | No | Multiple built-in preset voice options (first option selected by default) |
| `sample_rate` | Output sample rate in Hz. (default: "24000") | COMBO | Yes | `"8000"`<br />`"16000"`<br />`"24000"`<br />`"32000"`<br />`"44100"`<br />`"48000"` |
| `speech_rate` | Speaking speed. 0 = normal, 100 = 2.0x, -50 = 0.5x. (default: 0) | INT | Yes | -50 to 100 |
| `loudness_rate` | Loudness. 0 = normal, 100 = 2.0x, -50 = 0.5x. (default: 0) | INT | Yes | -50 to 100 |
| `pitch_rate` | Pitch shift in semitones (-12 to 12). (default: 0) | INT | Yes | -12 to 12 |
| `seed` | Seed controls whether the node should re-run; results are non-deterministic regardless of seed. (default: 42) | INT | Yes | 0 to 2147483647 |
| `model` | Model version. The multilingual variant supports 20 languages and per-sentence timing via `[5.5s:8.0s]` timestamps. (default: "seed-audio-1.0-multilingual") | COMBO | No | `"seed-audio-1.0-multilingual"`<br />`"seed-audio-1.0"` |
| `model` | Model version. `seed-audio-1.0-multilingual` supports 20 languages and per-sentence timing control via `[5.5s:8.0s]` timestamps. `seed-audio-1.0` supports English and Chinese only, without timing control. (default: "seed-audio-1.0-multilingual") | COMBO | No | `"seed-audio-1.0-multilingual"`<br />`"seed-audio-1.0"` |

### Parameter Constraints

- **Reference mode dependencies**: The `reference_mode` parameter determines which other inputs are required:
- **"text only"**: No additional inputs required. The prompt must not contain @AudioN tags.
- **"audio reference"**: Requires at least one of `reference_audio_1`, `reference_audio_2`, or `reference_audio_3` to be connected. Reference clips must be connected in order without gaps (e.g., _1, then _2, then _3). Each clip is limited to 30 seconds maximum duration. The prompt must reference connected clips using @Audio1, @Audio2, @Audio3 tags.
- **"image reference"**: Requires `reference_image` to be connected. The prompt must not contain @AudioN tags.
- **"preset voice"**: Requires `preset_voice` to be selected. The prompt must not contain @AudioN tags (the entire prompt is read in the selected voice).
- **"audio reference"**: Requires at least one of `reference_audio_1`, `reference_audio_2`, or `reference_audio_3` to be connected. Reference clips must be connected in order without gaps. Each clip is limited to 30 seconds maximum duration. If @AudioN tags are used in the prompt, the highest tag number must not exceed the number of connected reference clips.
- **"image reference"**: Requires `reference_image` to be connected. @AudioN tags are not used; the prompt should contain only the text to synthesize.
- **"preset voice"**: Requires a preset voice to be selected. The whole prompt is read in the selected voice; @AudioN tags are not used as references, and tags such as @Audio2 or higher are rejected.

- **Audio reference ordering**: When using "audio reference" mode, reference audio inputs must be connected sequentially starting from `reference_audio_1` without gaps. For example, you can connect _1 and _2, but not _1 and _3 without _2.
- **Audio reference ordering**: In "audio reference" mode, reference audio inputs must be connected sequentially starting from `reference_audio_1` without gaps. For example, you can connect `reference_audio_1` and `reference_audio_2`, but not `reference_audio_1` and `reference_audio_3` without `reference_audio_2`.

- **Maximum audio tags**: The prompt can reference up to 3 audio clips (@Audio1, @Audio2, @Audio3) when in "audio reference" mode. The highest numbered tag must not exceed the number of connected reference audio inputs.
- **Maximum audio tags**: In "audio reference" mode, up to 3 reference clips can be connected (@Audio1, @Audio2, @Audio3), and the highest @AudioN tag in the prompt cannot exceed the number of connected reference audio inputs.

- **Model differences**: The "seed-audio-1.0-multilingual" model supports 20 languages (English, Chinese, Japanese, Korean, Mexican & Castilian Spanish, Indonesian, German, Brazilian Portuguese, French, Thai, Vietnamese, Malay, Filipino, Italian, Russian, Dutch, Polish, Turkish, Swedish) plus per-sentence timing control using timestamps in the format `[5.5s:8.0s]`. The "seed-audio-1.0" model supports English and Chinese only, without timing control.
- **Model differences**: The `seed-audio-1.0-multilingual` model supports 20 languages (English, Chinese, Japanese, Korean, Mexican & Castilian Spanish, Indonesian, German, Brazilian Portuguese, French, Thai, Vietnamese, Malay, Filipino, Italian, Russian, Dutch, Polish, Turkish, Swedish) plus per-sentence timing control using timestamps in the format `[5.5s:8.0s]`. The `seed-audio-1.0` model supports English and Chinese only, without timing control.

## Outputs

Expand Down
2 changes: 0 additions & 2 deletions built-in-nodes/ConvertDictionaryToString.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,8 +6,6 @@ icon: "circle"
mode: wide
---

Convert Dictionary to String

This node converts a dictionary (a collection of key-value pairs) into a text string in JSON format. You can control the indentation level to make the output more readable or compact.

## Inputs
Expand Down
4 changes: 3 additions & 1 deletion built-in-nodes/DA3GeometryToMesh.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,13 +13,15 @@ This node converts a DA3_GEOMETRY packet into a 3D mesh by unprojecting the dept
| Parameter | Description | Data Type | Required | Range |
|-----------|-------------|-----------|----------|-------|
| `da3_geometry` | The DA3_GEOMETRY packet containing depth map, optional confidence map, optional sky map, and source image | DA3_GEOMETRY | Yes | - |
| `batch_index` | Which image of a batch to convert. Per-image vertex counts differ so batches cannot be stacked (default: 0) | INT | Yes | 0 to 4096 |
| `batch_index` | Which image of a batch to convert. Per-image vertex counts differ so batches cannot be stacked (default: 0). Must be less than the batch size of the input geometry, otherwise an error is raised | INT | Yes | 0 to 4096 |
| `decimation` | Vertex stride. 1 = full resolution, 2 = half, etc. (default: 1) | INT | Yes | 1 to 8 |
| `discontinuity_threshold` | Drop triangles whose 3x3 depth span exceeds this fraction. 0 = off (default: 0.04) | FLOAT | Yes | 0.0 to 1.0 |
| `confidence_threshold` | Exclude pixels whose per-image normalised confidence is below this value. 0 = keep all, 1 = keep only the single most confident pixel. Used when the geometry has a confidence map (Small/Base models) (default: 0.1) | FLOAT | Yes | 0.0 to 1.0 |
| `use_sky_mask` | Exclude sky-probability pixels (sky >= 0.5) from the mesh. Used when the geometry has a sky map (Mono/Metric models) (default: True) | BOOLEAN | Yes | True or False |
| `texture` | Use the source image as a base color texture (default: True) | BOOLEAN | Yes | True or False |

Pixels with non-finite, zero, or negative depth values are always excluded from the mesh. An error is raised if the resulting mesh is empty; the error message suggests raising `discontinuity_threshold`, lowering `confidence_threshold`, or disabling `use_sky_mask`.

## Outputs

| Output Name | Description | Data Type |
Expand Down
9 changes: 8 additions & 1 deletion built-in-nodes/DA3GeometryToPointCloud.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,11 +18,18 @@ Convert a depth map from a DA3_GEOMETRY object into a 3D point cloud. It applies
| `use_sky_mask` | Exclude sky-probability pixels (sky >= 0.5). Used when the geometry has a sky map (Mono/Metric models). (default: True) | BOOLEAN | Yes | True or False |
| `downsample` | Take every Nth pixel (1 = full resolution). Higher values give fewer points and faster processing. (default: 1) | INT | Yes | 1 to 16 |

**Notes:**
- `batch_index` must be smaller than the batch size of the input geometry; otherwise the node raises an error.
- If filtering removes all pixels, the node raises an error. Lowering `confidence_threshold` or disabling `use_sky_mask` can prevent this.
- `confidence_threshold` is only applied when the geometry includes a confidence map (Small/Base models).
- `use_sky_mask` is only applied when the geometry includes a sky map (Mono/Metric models).
- When `downsample` is greater than 1, the camera intrinsics are scaled accordingly so the projected points remain correct.

## Outputs

| Output Name | Description | Data Type |
|-------------|-------------|-----------|
| `point_cloud` | A point cloud object containing filtered 3D points, optional colors, and optional confidence values | DA3_POINT_CLOUD |
| `point_cloud` | A point cloud containing filtered 3D points, optional colors, and optional confidence values | DA3_POINT_CLOUD |

> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/DA3GeometryToPointCloud/en.md)

Expand Down
Loading
Loading