# Image AI Tools

These are one-click AI operations you can run on an existing image node. Most are accessed via right-click context menu → **AI Tools**, plus a couple of quick buttons in the node side toolbar.

## Upscale Image

**Menu path:** Right-click image node → **AI Tools** → **Upscale Image**  
**Model:** Topaz High Fidelity V2  
**Options:** 2x, 3x, 4x scaling

Choose your upscale factor:
- **2x** — 5 credits
- **3x** — 9 credits
- **4x** — 14 credits

The upscaled image replaces the original and preserves all detail using Topaz's high-fidelity algorithm.

## Remove Background

**Menu path:** Right-click image node → **AI Tools** → **Remove Background**  
**Model:** Bria  
**Cost:** 4 credits

Removes the background from your image, leaving the subject isolated. Works best with clear subject edges and is safe for commercial use (trained on licensed data).

## Change Aspect Ratio

**Menu path:** Right-click image node → **AI Tools** → **Change Aspect Ratio**  
**Model:** Flux 2 (Outpainting/Extend)  
**Cost:** 9 credits  
**Preset ratios:**
- Ultra Wide (21:9)
- Landscape (16:9)
- Photo (3:2)
- Standard (4:3)
- Classic (5:4)
- Square (1:1)
- Portrait (4:5)
- Tall (3:4)
- Vertical (2:3)
- Story (9:16)

This outpaints (extends) your image to a new aspect ratio by generating new content to fill the expanded areas. The original subject stays intact and centered, and generated areas blend seamlessly with existing content. This differs from the chat bar's aspect-ratio picker, which affects generation constraints before creating an image.

## Extract Color Palette

**Menu path:** Right-click image node → **AI Tools** → **Extract Color Palette**  
**Cost:** 5 credits

Analyzes your image and generates a set of dominant-color swatches. Each swatch appears as a new image node on the canvas, showing the extracted color palette.

## Crop

**Menu path:** Node side toolbar → **Crop** button (scissors icon)  
**Cost:** Free (creates new nodes from selection)

Opens an interactive crop dialog where you can:
- **Draw freely** — drag a rectangle anywhere to crop a custom area
- **Use grid presets** — split your image into grids (2×2, 1×2, 2×1, 1×3, 3×1) and select which cells to keep
- **Drag handles** — resize by edges or corners
- **Move the selection** — drag inside the selected area to reposition it
- **Adjust interior splits** — drag the grid lines to adjust split positions
- **Right-click a split** — delete it

Each selected cell becomes a separate image node on the canvas.

## New Angle

**Menu path:** Right-click image node → **AI Tools** → **New Angle**  
**Model:** Qwen (Multiple Angles)  
**Cost:** Depends on model selection (typically 9 credits)

Opens the **New Angle Dialog** with a 3D sphere preview. Use three interactive sliders to define the camera position:

- **Horizontal Angle (Azimuth):** -180° to 180° (or 0°–360°)
  - 0° = front
  - 90° = right
  - 180° = back
  - 270° = left
- **Vertical Angle (Elevation):** -30° to 90°
  - -30° = low upward angle
  - 0° = eye level
  - 90° = bird's-eye view
- **Zoom (Distance):** 0–10
  - 0 = wide/far shot
  - 5 = medium
  - 10 = close-up

Drag the 3D camera model in the preview sphere to adjust angles interactively. Click the **Generate** button to create the new view.

## New Perspective

**Menu path:** Right-click image node → **AI Tools** → **New Perspective**  
**Model:** Flux 2  
**Cost:** 9 credits

Generate one of these predefined camera views in one click:

- **Front View** — Straight-on face perspective
- **Rear View** — Back at 0° angle
- **Side View** — 90° profile (left side)
- **Right Side View** — 90° profile (right side)
- **3/4 Front Left** — 45° angle from front left
- **3/4 Front Right** — 45° angle from front right
- **3/4 Rear Left** — 45° angle from back left
- **3/4 Rear Right** — 45° angle from back right

Each perspective generates a new angle of the subject while keeping it in its place—only the camera viewpoint changes, so backgrounds reflect what's naturally visible from that angle.

## Image-to-3D

**Menu path:** Chat bar → Switch category to **"3D"** (red tab), then upload an image

Converts a 2D image into a 3D model (GLB file) which you can drop into the [3D scene editor](/docs/product/editor-3d).

**Auto-selected models** (first available in your plan):
1. Rodin v2.5
2. Rodin v2
3. Trellis 2
4. Hunyuan 3D Pro

**General process:**
1. Switch the chat category tab to **3D** (marked in red)
2. Select your preferred 3D model from the model dropdown
3. Upload your reference image(s)
4. (Optional) Adjust model-specific settings:
   - **Rodin v2.5:** Quality tier, mesh detail, PBR materials, HD textures, HighPack add-on
   - **Trellis 2:** Resolution (512px/1024px/1536px), texture size
   - **Hunyuan 3D Pro:** Generation type (textured or geometry-only), PBR materials, face count, up to 8 reference views
5. Click **Generate** — the 3D model outputs as a GLB file you can import to the 3D scene

Credit cost varies by model and settings (typically 63–168 credits, or up to 336 with Rodin v2.5 Extreme-High tier + HighPack).

---

**Note:** All AI Tools use your plan's credit balance. Insufficient credits will prevent generation. Use these operations to enhance, modify, and expand your designs without leaving the canvas.