Qwen-Image-2.1-PE-T2I-GGUF
Qwen-Image-2.1-PE-T2I is the text-to-image prompt-rewriting model for Qwen-Image-2.1, a fine-tuned Qwen3.5-VL-9B that turns a brief image request in any language into a detailed, expanded English prompt paired with a recommended aspect ratio, acting as the bridge between casual multilingual user requests (e.g., a short Chinese phrase describing a corgi playing guitar in the rain) and the precise, richly-detailed instructions the downstream 7B-parameter DiT-based Qwen-Image-2.1 generator needs for best results. After a
<think>reasoning block, it outputs a structured JSON object containing therewritten_promptand awh_ratiovalue (e.g.,16:9), which maps directly to standard render resolutions when passed into the DiffusersQwenImage21Pipeline. It's usable via standard Hugging FaceAutoModelForCausalLMloading, is intended purely as a preprocessing step ahead of image generation rather than a general-purpose chat model, and is released under the Qwen Research License Agreement.
[!NOTE] System Prompt — https://huggingface.co/Qwen/Qwen-Image-2.1-PE-T2I/blob/main/system_prompt.txt
Model Files
| File Name | Quant Type | File Size | File Link |
|---|---|---|---|
| Qwen-Image-2.1-PE-T2I.BF16.gguf | BF16 | 17.9 GB | Download |
| Qwen-Image-2.1-PE-T2I.Q3_K_L.gguf | Q3_K_L | 4.93 GB | Download |
| Qwen-Image-2.1-PE-T2I.Q3_K_M.gguf | Q3_K_M | 4.62 GB | Download |
| Qwen-Image-2.1-PE-T2I.Q4_K_M.gguf | Q4_K_M | 5.63 GB | Download |
| Qwen-Image-2.1-PE-T2I.Q4_K_S.gguf | Q4_K_S | 5.35 GB | Download |
| Qwen-Image-2.1-PE-T2I.Q5_K_M.gguf | Q5_K_M | 6.47 GB | Download |
| Qwen-Image-2.1-PE-T2I.Q5_K_S.gguf | Q5_K_S | 6.31 GB | Download |
llama.cpp
LLM inference in C/C++ — https://github.com/ggml-org/llama.cpp