Qwen releases Qwen-Image-2.1-PE-T2I text-to-image model with prompt rewriting
Qwen · hf · 2026-09-20
Qwen published Qwen-Image-2.1-PE-T2I on Hugging Face, a text-to-image model with prompt-rewriting capability, shipped in safetensors under a custom license.
Related event: Qwen Releases Prompt-Rewriting Models for Image Generation(2 posts)→
More from Multimodal
- Flow Matching revisited: the simulation-free CNF training method behind today's generative models — burny_tech · 2026-09-21
- Qwen-Image-2.1 native 2K generation doubles as an upscaler — no extra nodes needed — sktksm · 2026-09-21
- FAL Interview: MiniMax H3 Max Won't Be Open-Sourced, Going Frontier Commercial — pilkyton · 2026-09-21
- Qwen Image 2.1 Hands-On: Stunning Lighting, Weak Physics and Hallucinations — CosmicTurtle44 · 2026-09-21
- 10 Copy-Paste Edit Prompts for Qwen Image Edit: Pose, Texture, Lighting, Style — listopalafoto · 2026-09-21
- MiniMax H3 Squeezes Jelly GTA Protagonists Out of a Tube — Physics Impressively Real — DeerWoodStudios · 2026-09-21