> For the complete documentation index, see [llms.txt](https://docs.agenticflow.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.agenticflow.ai/reference/nodes/generate_image_v2.md). # Generate Image V2 **Action ID:** `generate_image_v2` ## Description Use AI to generate images from your imagination. Simply describe what you want to see, and watch the AI bring it to life. ## Connection | Name | Description | Required | Category | | ------------------ | ------------------------------------------- | -------- | -------- | | PixelML Connection | The PixelML connection to call PixelML API. | True | pixelml | ## Input Schema ```json { "description": "Generate image node input.", "properties": { "prompt": { "description": "What you wish to see in the output image. A strong, descriptive prompt that clearly defines elements, colors, and subjects will lead to better results.", "title": "Prompt", "type": "string" }, "negative_prompt": { "description": "A blurb of text describing what you do not wish to see in the output image.", "title": "Negative Prompt", "type": "string" }, "guidance_scale": { "default": 8, "description": "The guidance scale of the generated image.", "exclusiveMinimum": 0, "maximum": 15, "title": "Guidance scale", "type": "number" }, "steps": { "default": 20, "description": "The number of steps to take in the generated image.", "exclusiveMinimum": 0, "maximum": 50, "title": "Steps", "type": "integer" }, "batch_size": { "default": 1, "description": "The number of images to generate in a batch.", "exclusiveMinimum": 0, "maximum": 8, "title": "Batch size", "type": "integer" }, "seed": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null, "description": "The seed to use for the generated image.", "title": "Seed" }, "aspect_ratio": { "default": "9:16_HD", "description": "The aspect ratio of the generated image.", "enum": [ "1:1", "3:4", "4:3", "9:16", "16:9", "1:1_HD", "3:4_HD", "4:3_HD", "9:16_HD", "16:9_HD", "1:1_FHD", "3:4_FHD", "4:3_FHD", "9:16_FHD", "16:9_FHD" ], "title": "Aspect ratio", "type": "string" } }, "required": [ "prompt", "negative_prompt" ], "title": "GenerateImageV2NodeInput", "type": "object" } ``` ## Output Schema ```json { "description": "Generate image node output.", "properties": { "images": { "items": { "type": "string" }, "title": "Image output", "type": "array" } }, "required": [ "images" ], "title": "GenerateImageV2NodeOutput", "type": "object" } ``` ## How It Works This node uses PixelML's advanced AI image generation models to create images from text descriptions. You provide a detailed prompt describing what you want to see, along with a negative prompt specifying what to avoid. The AI processes your description through multiple diffusion steps, guided by the guidance scale parameter, to generate high-quality images. You can control quality through the steps parameter, generate multiple variations with batch\_size, and use seeds for reproducibility. ## Usage Examples ### Example 1: Professional Product Photography **Input:** ``` prompt: "Professional product photo of a luxury smartwatch on marble surface, studio lighting, soft shadows, elegant composition, 8k, photorealistic" negative_prompt: "blurry, low quality, distorted, cartoon, illustration, amateur" guidance_scale: 10 steps: 30 batch_size: 4 aspect_ratio: "1:1_HD" ``` **Output:** ``` images: [ "https://pixelml.com/output/smartwatch_var1.jpg", "https://pixelml.com/output/smartwatch_var2.jpg", "https://pixelml.com/output/smartwatch_var3.jpg", "https://pixelml.com/output/smartwatch_var4.jpg" ] ``` ### Example 2: Social Media Marketing Visual **Input:** ``` prompt: "Vibrant abstract background with flowing gradient colors from blue to purple, modern, energetic, suitable for Instagram story, vertical format" negative_prompt: "dull, boring, grayscale, text, watermark, people" guidance_scale: 8 steps: 25 batch_size: 1 seed: 42 aspect_ratio: "9:16_FHD" ``` **Output:** ``` images: ["https://pixelml.com/output/gradient_background.jpg"] ``` ### Example 3: Concept Art for Game Development **Input:** ``` prompt: "Fantasy medieval castle on mountain peak, dramatic sunset, clouds, epic scale, detailed architecture, concept art style, trending on artstation" negative_prompt: "modern buildings, cars, people, realistic photo, blurry" guidance_scale: 12 steps: 40 batch_size: 2 aspect_ratio: "16:9_FHD" ``` **Output:** ``` images: [ "https://pixelml.com/output/castle_concept1.jpg", "https://pixelml.com/output/castle_concept2.jpg" ] ``` ## Common Use Cases * **Marketing Content Creation**: Generate eye-catching visuals for social media posts, advertisements, and promotional materials * **Product Visualization**: Create product mockups and lifestyle images without expensive photoshoots * **Website Design**: Generate hero images, backgrounds, and visual assets for web pages and landing pages * **Concept Art**: Develop initial concept designs for games, films, or creative projects * **Content Variation Testing**: Generate multiple versions of the same concept to A/B test different visual approaches * **Rapid Prototyping**: Quickly visualize ideas for presentations, pitches, or client proposals * **Illustration and Art**: Create unique illustrations, artwork, and creative visuals for various projects ## Error Handling | Error Type | Cause | Solution | | ------------------------ | ------------------------------------------ | -------------------------------------------------------------------------------- | | Empty Prompt | Prompt field is empty or null | Provide a descriptive text prompt for the image you want to generate | | Invalid Guidance Scale | Guidance scale outside 0-15 range | Set guidance scale between 0 and 15 (recommended: 7-12) | | Invalid Steps | Steps value exceeds maximum of 50 | Reduce steps to 50 or less (recommended: 20-40 for balance of quality and speed) | | Batch Size Exceeded | Batch size greater than 8 | Reduce batch\_size to 8 or fewer images per generation | | Invalid Aspect Ratio | Aspect ratio value not in supported list | Choose from supported ratios (1:1, 16:9, 9:16, etc.) with HD or FHD variants | | PixelML Connection Error | Invalid or missing PixelML API credentials | Verify your PixelML connection is properly configured with valid API key | | Generation Timeout | Image generation takes too long | Reduce steps count, batch size, or resolution to speed up generation | ## Notes * **Prompt Quality**: More detailed and descriptive prompts produce better results. Include style, lighting, composition, and quality descriptors * **Negative Prompts**: Use negative prompts to actively exclude unwanted elements like blur, distortion, or specific objects * **Guidance Scale**: Higher values (10-15) follow prompts more strictly, lower values (3-7) allow more creative freedom * **Steps vs Speed**: More steps (30-50) produce higher quality but take longer. 20-30 steps balance quality and speed * **Batch Generation**: Generate multiple variations (batch\_size 2-8) to select the best result for your needs * **Seed Control**: Use the same seed to reproduce similar images or omit for random variations * **Aspect Ratios**: HD variants are 1024px, FHD variants are 1920px on the longest side. Choose based on your output needs * **Processing Time**: Generation typically takes 10-60 seconds depending on steps, batch size, and resolution