akhaliq/minimax-h3-image-pdmd-2step
text-to-image model by akhaliq
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.
A/B it on your promptsPackage your LoRA like this A true 2-step mode for MiniMaxAI/MiniMax-H3-Image: the pDMD 2-NFE LoRA (arXiv 2609.35768, rank 128 over attention + FFN of all 50 blocks) merged into the official 33.1B image transformer, at the model's native 4096×4096 (16 MP) — no CFG, prompts as written. The stock checkpoint is step-distilled for its fixed 6-step PDD schedule; this LoRA lands a finished image in 2 denoising evaluations on a plain flow-matching grid. This repo ships the LoRA in two layouts: keys (transformer.transformerblocks.N.attn.toq…, split QKV). Merge this into any diffusers MiniMaxH3Transformer3DModel — P-H3-Image's, or the official checkpoint after the on-the-fly conversion in rendergrid.py. block-diagonal qkvproj, SwiGLU halves swapped back to [gate; value]), by Iwannapose, mirrored here for one-stop use. This is the file for ComfyUI and other native-naming stacks. pruned bf16 diffusion model with the pDMD LoRA pre-merged (208 deltas in fp32, base metadata preserved), verified…
Read the full model card ↗ · Preview checked 2026-11-13T06:58:02.150Z
Inside the original model card — Document outline
- MiniMax-H3-Image pDMD 2-Step LoRA
- Usage (ComfyUI)
- Detail pass in ComfyUI (verified)
- Samples — 2 steps
- Showcase — 2 steps, native 16 MP at every aspect ratio
- Optional detail pass — and which one to use
- Heavyweight: Open-H3-Regenerate-2K-IC
- How it was run (and how to reproduce)
- Usage (diffusers)
- Prompting
- 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
akhaliq/minimax-h3-image-pdmd-2step is a text-to-image model repository published by akhaliq on Hugging Face. The source reports the diffusers 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
- diffusers
- Recent downloads (30 days)
- 23,675
- Cumulative likes
- 50
- Hugging Face trending score
- 50
- Reported safetensors parameters
- 33,122,992,896
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-11-10T15:21:45.000Z
- Last modified
- 2026-11-11T00:53:30.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: MiniMaxAI/MiniMax-H3-Image
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 2026-11-14T06:56:53.534Z. 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