VPick AI Image Generator

VPick Image Generator

Multi-model AI image generation on a visual canvas — Midjourney, Grok, nano-banana, Seedream — with reference image support, style transfer, and batch generation. Powered by VPick.

Security & Data Handling

Prerequisites

1. Sign up at vpick.10xboost.org (Google OAuth — new users get $1 free credit) 2. Get your MCP link: Go to Settings → copy your MCP Server URL (contains your auth token) 3. Add to Claude: Paste the MCP link into Claude settings as a Connector — no install, no API keys needed

Available Image Models

| Model | Cost | Output | Best For | |-------|------|--------|----------| | nano-banana-2 | $0.16/image | 1 image | Default, fast, multi-reference support | | Midjourney Relaxed | $0.045/grid | 4 images (grid) | Budget artistic generation | | Midjourney Fast | $0.12/grid | 4 images (grid) | Quick artistic generation | | Midjourney Turbo | $0.24/grid | 4 images (grid) | Fastest Midjourney | | Grok Imagine | $0.06/call | 6 images (T2I) or 2 (I2I) | Budget bulk generation | | Seedream 5.0 Lite | $0.0825/image | 1 image (2K) | High resolution, affordable | | Seedream 5.0 HD | $0.0825/image | 1 image (3K) | Ultra high resolution |

Aspect Ratios: 1:1, 16:9, 9:16, 3:4, 4:3 (all models)

Core Workflow

Step 1: Set Up

Check user's canvas and project:

get_canvas          → See current state
list_projects       → Check existing projects
create_project      → Start fresh if needed

Step 2: Create Image Generator Node

add_node(type: "image-generator", name: "My Image")

Step 3: Set the Prompt

Option A — Direct prompt:

update_node(id: "", data: { prompt: "a cyberpunk cityscape at sunset, neon lights, rain reflections" })

Option B — Connect a Text node:

add_node(type: "text", name: "Prompt", data: { content: "a cyberpunk cityscape at sunset" })
connect_nodes(sourceId: "", targetId: "", sourceHandle: "text-out", targetHandle: "prompt-in")

Step 4: Add Reference Images (Optional)

Reference images guide the generation style or subject. Up to 10 reference images supported.

upload_image(url: "https://example.com/reference.jpg")
connect_nodes(sourceId: "", targetId: "", sourceHandle: "file-out", targetHandle: "image-in")

Use @NodeLabel in prompts to reference connected images:

"A portrait in the style of @reference, vibrant colors"

The @reference is resolved at generation time to the connected image URL.

Step 5: Generate

run_image_generator(
  nodeId: "",
  prompt: "a cyberpunk cityscape at sunset, neon lights",
  model: "nano-banana-2",
  aspectRatio: "16:9"
)

Midjourney-specific options:

run_image_generator(
  nodeId: "",
  prompt: "a cyberpunk cityscape at sunset",
  model: "midjourney",
  aspectRatio: "16:9",
  mjSpeed: "fast",        // "relaxed", "fast", "turbo"
  mjVersion: "7.0"        // Midjourney version
)

Grok — auto-detects T2I vs I2I:

Step 6: Browse Results

Models may generate multiple images:

Check results:

get_node(id: "")   → See generatedImageUrl, status
list_nodes                      → Overview of all nodes

Step 7: Use Generated Images

Generated images can be used as input for:

connect_nodes(sourceId: "", targetId: "", sourceHandle: "image-out", targetHandle: "start-image-in")

Common Use Cases

Character Design (White Background References)

run_image_generator(
  nodeId: "",
  prompt: "full body portrait of a young woman, casual outfit, white background, isolated figure, front view",
  model: "nano-banana-2",
  aspectRatio: "3:4"
)

Batch Generation

add_node(type: "image-generator", name: "Variant A")
add_node(type: "image-generator", name: "Variant B")
add_node(type: "image-generator", name: "Variant C")
run_image_generator(nodeId: "", prompt: "sunset beach, warm tones", model: "midjourney")
run_image_generator(nodeId: "", prompt: "sunset beach, cool tones", model: "grok-imagine")
run_image_generator(nodeId: "", prompt: "sunset beach, dramatic", model: "nano-banana-2")

Style Transfer with References

upload_image(url: "https://example.com/style-reference.jpg")
connect_nodes(sourceId: "", targetId: "", sourceHandle: "file-out", targetHandle: "image-in")
run_image_generator(
  nodeId: "",
  prompt: "a portrait in the style of @style-reference, detailed, high quality",
  model: "nano-banana-2"
)

auto_layout(nodeIds: [...], direction: "horizontal", spacing: 200)
create_group(nodeIds: [...], overrides: { label: "Character Designs", color: "#E57373" })

list_generated_files(limit: 20, model: "midjourney")   → Recent generations filtered by model
get_generation_stats                                     → Cost breakdown by model

1. Sign up at vpick.10xboost.org (Google OAuth — new users get $1 free credit) 2. Get your MCP link: Go to Settings → copy your MCP Server URL (contains your auth token) 3. Add to Claude: Paste the MCP link into Claude settings as a Connector — no install, no API keys needed