PulseAugur
EN
LIVE 07:33:48
Français(FR) P-JiT : un modèle text-to-image de 2 milliards de paramètres, aux poids en Apache 2.0, que vous pouvez réutiliser dans vos projets. Il a été entraîné sur 660 mi

P-JiT text-to-image model released with open weights

By PulseAugur Editorial · [1 sources] ·

A new text-to-image model named P-JiT has been released, featuring 2 billion parameters and weights available under the Apache 2.0 license for project reuse. This model was trained using 660 million samples, with the computational cost for training estimated at $21,000. AI

IMPACT Provides a new open-source option for text-to-image generation, potentially fostering further development and application in creative and technical fields.

RANK_REASON Release of a new open-source AI model. [lever_c_demoted from research: ic=1 ai=1.0]

Read on Mastodon — mastodon.social →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

P-JiT text-to-image model released with open weights

How we ranked this

Signal score
17 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Release of a new open-source AI model. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. Mastodon — mastodon.social TIER_1 Français(FR) · camilleroux ·

    P-JiT: A 2-billion parameter text-to-image model with weights under Apache 2.0 that you can reuse in your projects. It was trained on 660 mi

    P-JiT : un modèle text-to-image de 2 milliards de paramètres, aux poids en Apache 2.0, que vous pouvez réutiliser dans vos projets. Il a été entraîné sur 660 millions d'échantillons pour 21 000 $ de calcul. ⬇️ https://www. linum.ai/field-notes/pjit-21k # AI # LLM 📬 Ma veille dev,…

    LINKS linum.ai/…/pjit-21k camilleroux.com/veille

RELATED ENTITIES

RELATED TOPICS