Pinkstack/LiliPixel-V1-190M

text-to-image model by Pinkstack

Open original source ↗

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.

This model release is a from-scratch open weight text-to-pixel-art diffusion transformer (191M trainable parameters) that generates pixel "art"/sprite style images at native 16x16, 32x32 or 64x64 resolution. (64 pixel res also has realism toggle) Caption tokens and image tokens share one sequence with full self-attention (single-stream DiT). Text is encoded by a frozen MongoDB/voyage-4-nano (346M parameters, not included in the weights, downloaded automatically on first use). The model needs roughly just 1GB of memory with lossless BF16 inference. warning: 16x16 and 32x32 are always with a transparent background, 64x64 is never transparent. Requires transformers>=4.56 and trustremotecode=True (the text encoder uses custom code; internet needed on first load). LiliPixel is a custom diffusers pipeline with its own text encoder, so ComfyUI's built-in checkpoint loaders can't open it. A single-file custom node wraps the pipeline instead. The first run needs internet to download the model and the text encoder. Using the workflow…

Pinkstack/LiliPixel-V1-190M on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-11-22T09:57:32.031Z

Inside the original model card — Document outline
  1. LiliPixel-V1 (16x16 / 32x32 / 64x64)
  2. Model details
  3. How to prompt
  4. Quickstart example
  5. ComfyUI
  6. Limitations
  7. Training
  8. Training data

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: openmdw-1.1. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

Pinkstack/LiliPixel-V1-190M is a text-to-image model repository published by Pinkstack 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)
141
Cumulative likes
34
Hugging Face trending score
32
Reported safetensors parameters
190,580,500
Architecture
Not reported
License
openmdw-1.1
Access
Not gated by Hugging Face
Created
2026-11-19T16:48:00.000Z
Last modified
2026-11-19T21:10:09.000Z

Compatibility and lineage

Reported languages: en

Base-model lineage was not included.

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

Source and freshness

Source: Hugging Face Hub. Metadata observed 2026-11-22T07:01:15.786Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related models

Comfy-Org/Qwen-Image-2.1

stabilityai/stable-diffusion-xl-base-1.0

Comfy-Org/Krea-2

Comfy-Org/MiniMax-H3-Image

abenzerps/Qwen-Image-2.1-Uncensored-Quantized

abenzerps/Qwen-Image-2.1-Uncensored-GGUF