Ideogram 4.0 Day-0 Support in ComfyUI: Open Weights and Structured Control
A 9.3B open-weights text-to-image model that reads JSON prompts like a spec sheet.
- Models
- Ideogram 4
- Reading Time
- 2 min
Workflow Overview
A 9.3B open-weights text-to-image model that reads JSON prompts like a spec sheet.
Content type: Workflow
Primary intent: Download
Required Models
- Ideogram 4
Setup Notes
- Install the required models before opening the workflow template.
- Use the download button above to import the workflow JSON into ComfyUI.
The open-source community witnesses a landmark moment! Ideogram unveils its debut publicly available foundation model, Ideogram 4.0, seamlessly integrated into ComfyUI right from release day.
This groundbreaking 9.3 billion-parameter text-to-image system, developed without pre-existing frameworks, stands as the go-to solution for designing posters, arranging layouts, or generating clear text—completely free from closed APIs. Experience it now.
Advanced Manipulation through Structured Formatting
Here's where Ideogram 4.0 proves its value. While standard textual requests yield images, employing an organized structure provides meticulous authority. Three capabilities unattainable via conventional prompts:
Color schemes: Apply up to 16 hexadecimal values per project (5 per component)
Spatial positioning: Define regions using
[y_min, x_min, y_max, x_max]in normalized 0–1000 coordinatesFormatted text components: Separate content strings from their visual styling specifications
Recommendation: Anchoring connections within prompts—through coordinates, hues, or elemental design—enhances precision. Model training leveraged extensively detailed scenes, rewarding explicit definitions.
Prompts Template Structure:
{ "high_level_description": "", "style_description": { "aesthetics": "", "lighting": "", "photo": "", "medium": "", "color_palette": [] # hexadecimal values }, "compositional_deconstruction": { "background": "", "elements": [ { "type": "obj", # for object "bbox": [], # y_min, x_min, y_max, x_max "desc": "", "color_palette": [] # hexadecimal values }, { "type": "text", # for text "text": "", # the text to render "bbox": [], # y_min, x_min, y_max, x_max "desc": "", "color_palette": [] # hexadecimal values } ] } }
Samples
Content Safety Mechanisms
The model incorporates native integrity checks—distinct from ComfyUI features. Generation blocks or blank outcomes signify internal moderation. Adjustment of prompts remains the solution, since this immutable component derives from base configuration.
Configuration Steps
Update Environment: Ensure ComfyUI reaches version 0.24.0
Template Acquisition: Retrieve the workflow configuration from the provided repository
Model Setup: Place assets according to workflow specifications
Operation: Utilize either textual instructions or organized formats in workflow execution
Access configurations: 🤗 Weights
Repository: Project Source
Celebrate innovation!