KavinduHansaka/Llama-3.2-1B-ImageGen

Hugging Face
TEXT GENERATIONPricing:Input $0.108 / Output $0.804Concurrent Unit Cost:1Model Size:1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Oct 2, 2025License:mitArchitecture:Transformer Open Weights Featherless Exclusive Warm

KavinduHansaka/Llama-3.2-1B-ImageGen is a 1 billion parameter Llama 3.2-based causal language model, finetuned by KavinduHansaka. This model is specialized for generating cinematic, detailed, and structured prompts for text-to-image models like Stable Diffusion XL and Flux. It excels at creating creative prompts suitable for diffusion-based image synthesis, rather than general-purpose chat. The model was finetuned using LoRA adapters on the prompt-gen-10k-flux-sdxl dataset.

Loading preview...

Model Overview

KavinduHansaka/Llama-3.2-1B-ImageGen is a 1 billion parameter, decoder-only causal language model built upon the meta-llama/Llama-3.2-1B architecture. Developed by KavinduHansaka, this model has been specifically finetuned using LoRA adapters (which were subsequently merged) to excel in image prompt generation.

Key Capabilities

  • Specialized Prompt Generation: Designed to produce cinematic, detailed, and structured prompts for leading text-to-image models such as Stable Diffusion XL and Flux.
  • Creative Output: Generates concise and creative prompts optimized for diffusion-based image synthesis.
  • LoRA Finetuned: Benefits from LoRA finetuning on the prompt-gen-10k-flux-sdxl dataset, enhancing its ability to craft effective image prompts.

Intended Use Cases

  • Direct Prompt Generation: Ideal for users needing stylized, cinematic, or structured prompts for various image synthesis tasks.
  • Downstream Finetuning: Can serve as a robust base model for further LoRA finetuning on style-specific datasets.
  • Integration into T2I Pipelines: Suitable for integration as a dedicated prompt generator within larger text-to-image pipelines.

This model is not intended for general-purpose chat or safety-critical applications, focusing solely on its specialized task of image prompt creation.

Finetunes
2 models