Qwen/Qwen-Image
Text-to-image diffusion model (20B parameters) from the Qwen-Image family, served via vLLM-Omni.
Shared DiT core across T2I, image editing, and layered-image variants; accelerated via Cache-DiT, TeaCache, and sequence parallelism
Text-to-image diffusion model (20B parameters) from the Qwen-Image family, served via vLLM-Omni.
Shared DiT core across T2I, image editing, and layered-image variants; accelerated via Cache-DiT, TeaCache, and sequence parallelism
View on HuggingFace
View on ModelScope