comfyui-wiki · Oct 11, 2026 · Oct 11, 2026
diff --git a/built-in-nodes/CameraAngle.mdx b/built-in-nodes/CameraAngle.mdx
@@ -0,0 +1,42 @@
+---
+title: "CameraAngle - ComfyUI Built-in Node Documentation"
+description: "This node picks a camera angle around a subject and turns that choice into two things: a camerainfo structure that 3D nodes can render, and a plain-English shot description you can"
+sidebarTitle: "CameraAngle"
+icon: "circle"
+mode: wide
+---
+
+This node picks a camera angle around a subject and turns that choice into two things: a `camera_info` structure that 3D nodes can render, and a plain-English shot description you can paste into a prompt. The subject sits at the origin of the scene, where downstream 3D nodes centre their models, so the angle you pick here matches the preview.
+
+Use it to frame a render before generating, or to describe a viewpoint such as `front view eye-level shot medium shot` for an image or video model. The 3D preview in the node shows the resulting camera position.
+
+## Inputs
+
+| Parameter | Description | Data Type | Required | Range |
+|-----------|-------------|-----------|----------|-------|
+| `horizontal_angle` | Azimuth around the subject in degrees: 0 is the front, 90 the right side, and 180 the back. (default: 0) | INT | Yes | 0 to 360 |
+| `vertical_angle` | Elevation in degrees. Negative values look up from below, positive values look down from above. (default: 0) | INT | Yes | -30 to 60 |
+| `zoom` | Lens zoom on the subject: 0 is a wide shot, 10 a close-up. The value is also carried into `camera_info.zoom`. (default: 5.0) | FLOAT | Yes | 0.0 to 10.0 (step 0.1) |
+| `image` | Optional reference image, shown on the front of the subject cube in the 3D preview. | IMAGE | No | - |
+
+## Outputs
+
+| Output Name | Description | Data Type |
+|-------------|-------------|-----------|
+| `camera_info` | Camera information for 3D nodes: position, look-at target, zoom factor, camera type, and field of view. The camera keeps a fixed 35 degree field of view and is placed 6 units from the target. | LOAD3DCAMERA |
+| `prompt` | Short shot description built from the angle, the elevation, and the distance, for example `front view eye-level shot medium shot`. | STRING |
+
+## Shot Description Terms
+
+The `prompt` output combines one term from each group below. Values are clamped to the widget ranges first.
+
+- Horizontal angle is split into eight 45 degree sectors: `front view`, `front-right quarter view`, `right side view`, `back-right quarter view`, `back view`, `back-left quarter view`, `left side view`, `front-left quarter view`.
+- Vertical angle becomes `low-angle shot` below -15 degrees, `eye-level shot` below 15, `elevated shot` below 45, and `high-angle shot` from 45 degrees up.
+- Zoom becomes `wide shot` below 2, `medium shot` below 6, and `close-up` at 6 or more.
+
+The `camera_info.zoom` factor scales the widget value onto 1.0 to 1.875, so zoom 0 gives 1.0 and zoom 10 gives 1.875.
+
+> 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/CameraAngle/en.md)
+
+---
+**Source fingerprint (SHA-256):** `8ed2cd186bc6ca02dbc8da006b2e9156245ef691a2257f286f6e32ffa480fd5d`
diff --git a/built-in-nodes/ClarityCrystalUpscaleNode.mdx b/built-in-nodes/ClarityCrystalUpscaleNode.mdx
@@ -0,0 +1,33 @@
+---
+title: "ClarityCrystalUpscaleNode - ComfyUI Built-in Node Documentation"
+description: "Upscale an image with Clarity AI's Crystal Upscaler, a high-fidelity upscaler that stays faithful to the original while restoring faces, skin, and fine texture."
+sidebarTitle: "ClarityCrystalUpscaleNode"
+icon: "circle"
+mode: wide
+---
+
+Upscale an image with Clarity AI's Crystal Upscaler, a high-fidelity upscaler that stays faithful to the original while restoring faces, skin, and fine texture. The image is sent to Clarity AI's API and the upscaled result is returned as an image.
+
+Selecting a `model` reveals the parameters specific to that model.
+
+## Inputs
+
+| Parameter | Description | Data Type | Required | Range |
+|-----------|-------------|-----------|----------|-------|
+| `model` | Model to use. Selecting a model reveals the parameters specific to it: `image`, `scale_factor`, and `creativity`. | DYNAMIC_COMBO | Yes | `"crystal-upscaler"` |
+| `image` | The image to upscale. Must contain exactly one image; image batches are not supported. | IMAGE | Yes | N/A |
+| `scale_factor` | Factor to multiply the image width and height by. The output is limited to 100 megapixels (default: 2.0). | FLOAT | Yes | 1.0 to 200.0 (step 0.1) |
+| `creativity` | Higher values let the model reconstruct more detail instead of strictly preserving the original. Has no effect on images whose shorter side is 256 pixels or less (default: 0). | INT | Yes | 0 to 10 |
+
+**Note:** The input image must be at least 2x2 pixels. The output is capped at 100 megapixels and 65535 pixels per side; a larger result raises an error, so use a smaller image or a lower `scale_factor`.
+
+## Outputs
+
+| Output Name | Description | Data Type |
+|-------------|-------------|-----------|
+| `IMAGE` | The upscaled image. | IMAGE |
+
+> 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/ClarityCrystalUpscaleNode/en.md)
+
+---
+**Source fingerprint (SHA-256):** `38c90cf7054a93477ee63c356c3fdf8ba38c7edaf1a337da7ac366cd9d746d9e`
diff --git a/built-in-nodes/CreateCameraInfo.mdx b/built-in-nodes/CreateCameraInfo.mdx
@@ -12,7 +12,7 @@ The Create Camera Info node builds a camera information structure for 3D renderi
 
 | Parameter | Description | Data Type | Required | Range |
 |-----------|-------------|-----------|----------|-------|
-| `mode` | How to define the camera: orbit angles, an explicit position, or a position + quaternion. | COMBO | Yes | `"orbit"`<br />`"look_at"`<br />`"quaternion"` |
+| `mode` | How to define the camera: orbit angles, an explicit position, or a position + quaternion. | DYNAMIC_COMBO | Yes | `"orbit"`<br />`"look_at"`<br />`"quaternion"` |
 | `target_x` | Look-at point (orbit pivot / aim). In orbit mode, move it to pan/translate the whole camera. Ignored in quaternion mode. Defaults to the origin. (default: 0.0) | FLOAT | No | -1000.0 to 1000.0 |
 | `target_y` | Y component of the target point. (default: 0.0) | FLOAT | No | -1000.0 to 1000.0 |
 | `target_z` | Z component of the target point. (default: 0.0) | FLOAT | No | -1000.0 to 1000.0 |
@@ -62,4 +62,4 @@ When `mode` is set to `"quaternion"`, the following parameters become available:
 > 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/CreateCameraInfo/en.md)
 
 ---
-**Source fingerprint (SHA-256):** `577c114130f72b753d5f15775fe05b3e1e734f5865cca32c576d042583f8e873`
+**Source fingerprint (SHA-256):** `5a9703e8e01ad2cd92a97da8d892c278765a9cef8bcd38e3336d1f73717d9895`
diff --git a/built-in-nodes/ElevenLabsTextToDialogue.mdx b/built-in-nodes/ElevenLabsTextToDialogue.mdx
@@ -16,9 +16,9 @@ The ElevenLabs Text to Dialogue node generates a multi-speaker audio dialogue fr
 |-----------|-------------|-----------|----------|-------|
 | `stability` | Voice stability. Lower values give broader emotional range, higher values produce more consistent but potentially monotonous speech. (default: 0.5) | FLOAT | Yes | 0.0 - 1.0 |
 | `apply_text_normalization` | Text normalization mode. 'auto' lets the system decide, 'on' always applies normalization, 'off' skips it. | COMBO | Yes | `"auto"`<br />`"on"`<br />`"off"` |
-| `model` | Model to use for dialogue generation. | COMBO | Yes | `"eleven_v3"` |
+| `model` | Model to use for dialogue generation (default: `"eleven_v4"`). | COMBO | Yes | `"eleven_v3"`<br />`"eleven_v4"`<br />`"eleven_v4_turbo"` |
 | `inputs` | Number of dialogue entries. Selecting a number creates that many text and voice input pairs. | DYNAMIC_COMBO | Yes | `"1"`<br />`"2"`<br />`"3"`<br />`"4"`<br />`"5"`<br />`"6"`<br />`"7"`<br />`"8"`<br />`"9"`<br />`"10"` |
-| `language_code` | ISO-639-1 or ISO-639-3 language code (e.g., 'en', 'es', 'fra'). Leave empty for automatic detection. (default: empty) | STRING | Yes | - |
+| `language_code` | ISO 639-1 language code (e.g., 'en', 'es', 'ja'). Leave empty for automatic detection. (default: empty) | STRING | Yes | - |
 | `seed` | Seed for reproducibility. (default: 1) | INT | Yes | 0 - 4294967295 |
 | `output_format` | Audio output format. | COMBO | Yes | `"mp3_44100_192"`<br />`"opus_48000_192"` |
 
@@ -42,4 +42,4 @@ Shared by all `inputs` options.
 > 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/ElevenLabsTextToDialogue/en.md)
 
 ---
-**Source fingerprint (SHA-256):** `95b16143391a2282c58ebc66561b85338a8ce1f87e0ec769405225599d2c76ae`
+**Source fingerprint (SHA-256):** `bff737be0c828990d7286de4372e995295a4716febd388d7cc02c2a9987a6c80`
diff --git a/built-in-nodes/ElevenLabsTextToSpeech.mdx b/built-in-nodes/ElevenLabsTextToSpeech.mdx
@@ -14,12 +14,12 @@ The ElevenLabs Text to Speech node converts written text into spoken audio using
 
 | Parameter | Description | Data Type | Required | Range |
 |-----------|-------------|-----------|----------|-------|
-| `model` | Model to use for text-to-speech. Selecting a model reveals its specific parameters. | DYNAMIC_COMBO | No | `"eleven_multilingual_v2"`<br />`"eleven_v3"` |
+| `model` | Model to use for text-to-speech. Selecting a model reveals its specific parameters. | DYNAMIC_COMBO | No | `"eleven_v4"`<br />`"eleven_v4_turbo"`<br />`"eleven_multilingual_v2"`<br />`"eleven_v3"` |
 | `voice` | Voice to use for speech synthesis. Connect from Voice Selector or Instant Voice Clone. | CUSTOM | Yes | N/A |
 | `text` | The text to convert to speech. Must contain at least one character. | STRING | Yes | N/A |
 | `stability` | Voice stability. Lower values give broader emotional range, higher values produce more consistent but potentially monotonous speech (default: 0.5). | FLOAT | No | 0.0 - 1.0 |
 | `apply_text_normalization` | Text normalization mode. 'auto' lets the system decide, 'on' always applies normalization, 'off' skips it. | COMBO | No | `"auto"`<br />`"on"`<br />`"off"` |
-| `language_code` | ISO-639-1 or ISO-639-3 language code (e.g., 'en', 'es', 'fra'). Leave empty for automatic detection (default: ""). | STRING | No | N/A |
+| `language_code` | ISO 639-1 language code (e.g., 'en', 'es', 'ja'). Leave empty for automatic detection (default: ""). | STRING | No | N/A |
 | `seed` | Seed for reproducibility (determinism not guaranteed) (default: 1). | INT | No | 0 - 2147483647 |
 | `output_format` | Audio output format. | COMBO | No | `"mp3_44100_192"`<br />`"opus_48000_192"` |
 
@@ -29,7 +29,7 @@ These parameters become available when `model` is set to `"eleven_multilingual_v
 
 | Parameter | Description | Data Type | Required | Range |
 |-----------|-------------|-----------|----------|-------|
-| `speed` | Speech speed. 1.0 is normal, &lt;1.0 slower, >1.0 faster (default: 1.0). | FLOAT | No | 0.7 - 1.3 |
+| `speed` | Speech speed. 1.0 is normal, &lt;1.0 slower, >1.0 faster (default: 1.0). | FLOAT | No | 0.7 - 1.2 |
 | `similarity_boost` | Similarity boost. Higher values make the voice more similar to the original (default: 0.75). | FLOAT | No | 0.0 - 1.0 |
 | `use_speaker_boost` | Boost similarity to the original speaker voice (default: False). | BOOLEAN | No | True / False |
 | `style` | Style exaggeration. Higher values increase stylistic expression but may reduce stability (default: 0.0). | FLOAT | No | 0.0 - 0.2 |
@@ -43,6 +43,14 @@ These parameters become available when `model` is set to `"eleven_v3"`.
 | `speed` | Speech speed. 1.0 is normal, &lt;1.0 slower, >1.0 faster (default: 1.0). | FLOAT | No | 0.7 - 1.3 |
 | `similarity_boost` | Similarity boost. Higher values make the voice more similar to the original (default: 0.75). | FLOAT | No | 0.0 - 1.0 |
 
+### eleven_v4 and eleven_v4_turbo Inputs
+
+These parameters become available when `model` is set to `"eleven_v4"` or `"eleven_v4_turbo"`.
+
+| Parameter | Description | Data Type | Required | Range |
+|-----------|-------------|-----------|----------|-------|
+| `similarity_boost` | Similarity boost. Higher values make the voice more similar to the original (default: 0.75). | FLOAT | No | 0.0 - 1.0 |
+
 ## Outputs
 
 | Output Name | Description | Data Type |
@@ -52,4 +60,4 @@ These parameters become available when `model` is set to `"eleven_v3"`.
 > 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/ElevenLabsTextToSpeech/en.md)
 
 ---
-**Source fingerprint (SHA-256):** `78ed1c6af2d0b1cc0293d725492a8b104b6d0c6bc18d9971b75047db946cdd33`
+**Source fingerprint (SHA-256):** `2f8aadca9f4fee9614ce4488aa206119ecf714518b7c0c340b1bfa766f59672e`
diff --git a/built-in-nodes/GeminiNanoBanana2V2.mdx b/built-in-nodes/GeminiNanoBanana2V2.mdx
@@ -14,14 +14,22 @@ This node generates or edits images by sending a text prompt to Google's Vertex
 
 | Parameter | Description | Data Type | Required | Range |
 |-----------|-------------|-----------|----------|-------|
-| `model` | Selects the Gemini image model to use. The chosen model determines the available resolution options and model-specific inputs. | DYNAMIC_COMBO | Yes | `"Nano Banana 2 (Gemini 3.1 Flash Image)"`<br />`"Nano Banana 2 Lite"` |
+| `model` | Selects the Gemini image model to use. The chosen model determines the available resolution options and model-specific inputs. | DYNAMIC_COMBO | Yes | `"Gemini Nano Banana 2.1"`<br />`"Nano Banana 2 (Gemini 3.1 Flash Image)"`<br />`"Nano Banana 2 Lite"` |
 | `prompt` | Text prompt describing the image to generate or the edits to apply. Include any constraints, styles, or details the model should follow. Must not be empty. (default: empty) | STRING | Yes | N/A |
 | `seed` | When the seed is fixed to a specific value, the model makes a best effort to provide the same response for repeated requests. Deterministic output isn't guaranteed. Also, changing the model or parameter settings, such as the temperature, can cause variations in the response even when you use the same seed value. By default, a random seed value is used. (default: 42) | INT | Yes | 0 to 18446744073709551615 |
 | `response_modalities` | Determines the response format. IMAGE returns only an image; IMAGE+TEXT returns an image and a text response. (default: IMAGE) Advanced parameter. | COMBO | Yes | `"IMAGE"`<br />`"IMAGE+TEXT"` |
 | `system_prompt` | Foundational instructions that dictate an AI's behavior. Defaults to a built-in prompt that instructs the model to always produce an image. Advanced parameter. | STRING | No | N/A |
 | `temperature` | Controls randomness in generation. Lower is more focused/deterministic. (default: 1.0) Advanced parameter. | FLOAT | No | 0.0 to 2.0 (step 0.01) |
 | `top_p` | Nucleus sampling threshold. Lower is more focused, higher more diverse. (default: 0.95) Advanced parameter. | FLOAT | No | 0.0 to 1.0 (step 0.01) |
 
+### Gemini Nano Banana 2.1 Inputs
+
+| Parameter | Description | Data Type | Required | Range |
+|-----------|-------------|-----------|----------|-------|
+| `aspect_ratio` | If set to 'auto', matches your input image's aspect ratio; if no image is provided, a 16:9 square is usually generated. (default: auto) | COMBO | Yes | `"auto"`<br />`"1:1"`<br />`"2:3"`<br />`"3:2"`<br />`"3:4"`<br />`"4:3"`<br />`"4:5"`<br />`"5:4"`<br />`"9:16"`<br />`"16:9"`<br />`"21:9"`<br />`"1:4"`<br />`"4:1"`<br />`"8:1"`<br />`"1:8"` |
+| `resolution` | Target output resolution. | COMBO | Yes | `"1K"`<br />`"2K"`<br />`"4K"` |
+| `thinking_level` | Selects the thinking level used by the model. | COMBO | Yes | `"MINIMAL"`<br />`"MEDIUM"`<br />`"HIGH"` |
+
 ### Nano Banana 2 (Gemini 3.1 Flash Image) Inputs
 
 | Parameter | Description | Data Type | Required | Range |
@@ -53,11 +61,11 @@ This node generates or edits images by sending a text prompt to Google's Vertex
 |-------------|-------------|-----------|
 | `IMAGE` | The generated or edited image. | IMAGE |
 | `STRING` | A text description or caption generated by the model. Empty when no text is returned, such as when `response_modalities` is set to `IMAGE`. | STRING |
-| `thought_image` | First image from the model's thinking process. Only available with `thinking_level` HIGH and IMAGE+TEXT modality. | IMAGE |
+| `thought_image` | First image from the model's thinking process. Only available with IMAGE+TEXT modality. | IMAGE |
 
 **Note:** The `STRING` output is empty when `response_modalities` is set to `IMAGE`. If the model does not generate an image in this mode, the node raises an error suggesting switching to IMAGE+TEXT to view the model's reasoning.
 
 > 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/GeminiNanoBanana2V2/en.md)
 
 ---
-**Source fingerprint (SHA-256):** `347d28aeb46aa91f7515a31c385a3e3f805a1861116a21dd2ef6575ab7fd4f3e`
+**Source fingerprint (SHA-256):** `238d661259e99fd0ce8cae227d873713bbad60aa5eccb32447be464317e39ddd`