molbal/ideogram-4-gguf

text-to-image model by molbal

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

Quantized GGUF diffusion transformer weights for Ideogram 4, converted from the original FP8 release for use with ComfyUI GGUF loader nodes. This repository contains GGUF files for the two Ideogram 4 diffusion components: These files are not a complete standalone Ideogram 4 package. Your workflow still needs the other runtime assets expected by Ideogram 4 in ComfyUI, such as the text or multimodal encoder components and VAE. Use these models with the ComfyUI nodes from molbal/ComfyUI-GGUF. Install that custom node repository into your ComfyUI customnodes folder, then restart ComfyUI. Place the downloaded .gguf files in one of ComfyUI's diffusion model folders: Load the files with Unet Loader (GGUF) or Unet Loader (GGUF/Advanced) in an Ideogram 4 workflow that accepts separate main and unconditional diffusion models. Each quant level is published for both the main transformer and the unconditional transformer. The main and unconditional models do not need to use the…

molbal/ideogram-4-gguf on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-09-21T06:53:39.893Z

Inside the original model card — Document outline

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Links from the model card

References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.

Ideogram 4 non-commercial license

Documentation belongs to its respective authors. Reported project/model license: other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

molbal/ideogram-4-gguf is a text-to-image model repository published by molbal on Hugging Face. A library was not reported.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task: text-to-image
Library: Not reported
Recent downloads (30 days): 68,746
Cumulative likes: 10
Hugging Face trending score: 0
Reported safetensors parameters: Not reported
Architecture: Not reported
License: other
Access: Not gated by Hugging Face
Created: 2026-06-12T17:10:42.000Z
Last modified: 2026-06-15T20:08:14.000Z

Compatibility and lineage

Language coverage was not reported.

Reported base models: ideogram-ai/ideogram-4-fp8

Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.

Use and evaluate

Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.

No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.

Model card and usage instructions

Model files and configuration

Community discussion