MatterWaveAI/grt-30m-image
text-to-image model by MatterWaveAI
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
GRT-30M-Image is a 100% Native Rotational Text-to-Image & Visual Patch Synthesis Language Model (29,371,239 total parameters, zero nn.Linear layers, zero nn.Conv2d layers) built on top of MatterWaveAI/grt-30m. Completing the bidirectional Vision symmetry alongside MatterWaveAI/grt-30m-vl (Image → Text), GRT-30M-Image synthesizes (B, 3, 224, 224) RGB images and discrete 4-codebook visual patch tokens directly from causal text representations through a purely rotational inverse Givens butterfly patch decoder (GRTPolarImageDecoderHead). We benchmarked all 8 classical geometric, symplectic, and…
Read the full model card ↗ · Preview checked 2026-11-07T08:12:05.719Z
Inside the original model card — Document outline
- GRT-30M-Image (MatterWaveAI/grt-30m-image)
- Architecture Summary
- Visual Synthesis Alignment Metrics (HuygensAdam / Circular Order Parameter $Rp$ Splay Torque)
- 8-Way Classical Geometric Optimizer Ablation (Intel Arc 140T XPU)
- Key Geometric Findings on Rotational Text-to-Image (GRTImage)
- Quickstart (transformers)
- Complete MatterWaveAI/grt-30m Research Suite on Hugging Face
- License
- Citation
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.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
MatterWaveAI/grt-30m-image is a text-to-image model repository published by MatterWaveAI on Hugging Face. The source reports the transformers library.
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
- transformers
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 29,963,585
- Architecture
- GRTImageForConditionalGeneration
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-11-07T06:14:34.000Z
- Last modified
- 2026-11-07T06:14:36.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: MatterWaveAI/grt-30m
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.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-07T06:54:27.277Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
stabilityai/stable-diffusion-xl-base-1.0
abenzerps/Qwen-Image-2.1-Uncensored-Quantized