Generate AI images with Higgsfield Canvas nodes

Demo summary
The user demonstrates how to connect a text prompt node and two image reference nodes to an image generator node in Higgsfield Canvas to create a specific cyberpunk character.
Step-by-step
- Right-click on the board and select Upload to add your reference images
- Add a text prompt node to the canvas
- Enter the descriptive text for your image into the prompt node
- Add an Image Generator node from the node list
- Connect the two reference image nodes to the Image Generator node
- Connect the prompt node to the Image Generator node
- Run the pipeline to generate the image
Tips
- Organize your nodes on the canvas to keep the workflow clear before connecting them
- Use specific reference images to guide the AI on complex details like a specific type of watch or lighting style
Highlights
“everything is perfectly working down here”
All demos from “Higgsfield Canvas: Full Walkthrough (Canvas + Workflow Builder)”
0:441:53Generate AI images with Higgsfield Canvas nodesCurrentThe user demonstrates how to connect a text prompt node and two image reference nodes to an image generator node in Higgsfield Canvas to create a specific cyberpunk character.Higgsfield· AI Image Generator
2:401:13Create AI video from image and prompt nodesThe demonstrator connects a previously generated image to a video generator node and adds a cinematic prompt to create a 12-second video with complex camera movements.Higgsfield· Image to Video
4:082:53Building a multi-stage AI video pipelineThe user builds a complex workflow in Higgsfield Canvas by connecting a generated video to a new video generator node to create a seamless transition into a new scene.Higgsfield· Video to Video- Watch “Higgsfield Canvas: Full Walkthrough (Canvas + Workflow Builder)” →
AI Image Generator
1:121:18Build a multi-model image generation workflow in Higgsfield CanvasThe user demonstrates how to add a prompt node and connect it to an image generator node, adjusting settings like aspect ratio and selecting models such as GPT image 2.RandomAI
2:301:37Benchmarking multiple AI models simultaneouslyThe creator shows how to connect a single prompt to three different image models (GPT image 2, Nano Banana 2, and Seedream 5.0 light) to compare their outputs side-by-side in one run.RandomAI
6:131:47Basic Image Generation with NodesA demonstration of creating a basic image generation workflow by connecting a prompt node to an image generation node using the GPT Image 2 model.DraftID
8:062:45Character Style Consistency with Prompt NodesThe video shows how to separate style and character prompts into different nodes to maintain a consistent 'miniature' look while swapping character subjects like an elf or a mech.DraftID
3:201:18Generate cinematic images with character and location tagsThe demonstration shows how to use '@' tags to reference saved characters and locations within a text prompt to generate consistent cinematic images in Higgsfield.Steven Wommack
11:132:02Compose and color grade a scene in HiggsfieldThe demo shows how to combine saved characters and locations into a single scene prompt, generate the image, and apply cinematic color grading and film grain effects.David Manning
2:091:54Build scenes in Higgsfield Cinema StudioThe user shows how to upload generated characters as references into Cinema Studio, select environments, and describe character interactions to create a static base scene.Money4Life
0:441:53Generate AI images with Higgsfield Canvas nodesCurrentThe user demonstrates how to connect a text prompt node and two image reference nodes to an image generator node in Higgsfield Canvas to create a specific cyberpunk character.Mhd Labs
0:321:14Generate an image using nodes in Higgsfield AIThe user demonstrates how to create a prompt node, connect it to an AI image generation node, and run the pipeline to generate an image of a cat within the Higgsfield AI canvas.Artturi Jalli
2:340:46Compare multiple AI image models on one canvasThe creator shows how to connect a single prompt to multiple different image generation nodes (like Cream 5.0 and Gro Imagine) to compare results side-by-side.Artturi Jalli
1:091:06Generate image prompts using LLM nodesThe demo shows connecting a headshot asset to a Claude Sonnet LLM node to generate an optimized prompt for a scuba diver image.Joseph Martin
2:561:18Multi-model image generation in HiggsfieldThe user demonstrates connecting a single prompt to multiple image nodes (Nano Banana Pro, GPT Image 2, and Nano Banana 2) to generate different variations simultaneously.Joseph Martin
Higgsfield