Unverified50% confidenceReleaseExact time
The SupraLabs team has released a lightweight text-to-image model, Supra2-IMG, with 100M parameters, trained from scratch using a DiT architecture, with an output resolution of 256×256, and it is fully open-source.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/21/2026
First Seen
Valid until: 12/20/2026
Sources
Related Entities
Related Claims
UnverifiedThe image generation feature of the AI1505 platform supports multiple models including Qianzhen GPG Yinban Machine 2, LALA BLALA, Jimon Cdream, and Kling, with a maximum output resolution of 4K.58% similarUnverifiedIMPALA由DeepMind于2018年发布，多个Actor在CPU上持续采样，Learner在GPU上专注训练，通过异步方式实现采样与训练的完全并行57% similarUnverifiedThe MiniCPM series is an open-source small model launched by ModelBest, focused on edge-side deployment and high cost-effectiveness.57% similarUnverifiedMini-AGI is an open-source project positioned as training a model with dynamic continual learning capabilities from scratch on a consumer-grade GPU with only 8GB of VRAM.57% similarUnverified轻量化模型通常采用YOLOv8-nano、MobileNet等经剪枝量化蒸馏处理的网络，在低分辨率下实现每秒30帧以上实时推理57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/939172API
curl https://kongchang.com/api/v1/knowledge/claims/939172MCP
get_claim(id=939172)