aifeifei798/Qwen3-1.7B-Flux-Prompt

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:2BQuant:BF16Ctx Length:32kLicense:apache-2.0Architecture:Transformer0.0K Open Weights Warm

aifeifei798/Qwen3-1.7B-Flux-Prompt is a 1.7 billion parameter language model, fine-tuned from Qwen3-1.7B-Instruct, specifically designed to expand short concepts into detailed, high-quality image prompts for Flux.1 image generation models. This lightweight model runs efficiently on various hardware and features an integrated system prompt within its tokenizer for streamlined usage. It excels at generating non-conversational, raw image prompts, making it ideal for automated prompt creation in stable diffusion pipelines.

Loading preview...

Qwen3-1.7B-Flux-Prompt: Image Prompt Generator

This model, developed by aifeifei798, is a specialized fine-tune of the Qwen3-1.7B-Instruct base model, optimized for generating detailed image prompts for Flux.1 image generation. It transforms simple user inputs into rich, descriptive prompts, ready for use in stable diffusion pipelines.

Key Capabilities

  • Dedicated Prompt Generation: Converts short concepts (e.g., "a cat") into elaborate, high-quality image prompts.
  • Lightweight and Fast: Built on a 1.7 billion parameter architecture, ensuring rapid execution even on less powerful hardware.
  • "Invisible" System Prompt: The system prompt is integrated directly into the tokenizer_config.json, eliminating the need for users to manually input complex instructions.
  • Non-Conversational Output: Delivers only the raw, generated prompt without any conversational filler, streamlining its integration into automated workflows.
  • Validated Quality: Tested for diversity and detail in its generated outputs, as demonstrated by provided examples.

Good For

  • Automated Image Prompt Creation: Ideal for developers and artists looking to quickly generate detailed prompts for AI image synthesis.
  • Flux.1 Users: Specifically fine-tuned and validated for compatibility with Flux.1 image generation models.
  • Resource-Constrained Environments: Its lightweight nature makes it suitable for deployment on older GPUs or CPUs where larger models might struggle.