Linum-AI/pjit-21k
text-to-image model by Linum-AI
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.
Sahil Chopra · Manu Chopra · Linum Blog post · Code · Apache-2.0 Five samples from the blog post's gallery. Their prompts and seeds are in the code repository. P-JiT 21K is the P-JiT architecture trained for longer (610M samples at 512px, 50M at 1024px), then post-trained with a variant of FDFO. The model was trained on dense captions of 50 to 80 words. The code repository ships a prompt upsampler that rewrites short prompts into captions of that kind with Claude Opus 5.5 through OpenRouter (it needs an OPENROUTERAPIKEY; --noupsample turns it off): The prompts and seeds of all five samples are in the code repository. Sampling defaults: 50 Euler steps, adaptive projected guidance at scale 15 against an empty negative prompt, initial noise at scale 4. The model was trained at five 1 MP sizes: 1024x1024, 864x1216, 1152x864, 1248x832 and 1280x720 (width x height). Text is encoded by…
Read the full model card ↗ · Preview checked 2026-11-08T09:39:31.352Z
Inside the original model card — Document outline
- A Text-to-Image Model Trained for $21K(Pyramid-JiT)
- Usage
- Files
- Limitations
- Citation
- Authorship
- About Linum
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
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
Linum-AI/pjit-21k is a text-to-image model repository published by Linum-AI on Hugging Face. The source reports the pjit-21k 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
- pjit-21k
- Recent downloads (30 days)
- 212
- Cumulative likes
- 53
- Hugging Face trending score
- 53
- Reported safetensors parameters
- 2,184,091,606
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-11-03T14:50:23.000Z
- Last modified
- 2026-11-03T20:23:29.000Z
Compatibility and lineage
Language coverage was not reported.
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.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-08T06:53:26.831Z. 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