63 lines
1.9 KiB
Markdown
63 lines
1.9 KiB
Markdown
|
---
|
||
|
|
base_model: meta-llama/Llama-3.2-3B
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
datasets:
|
||
|
|
- ABDALLALSWAITI/flux_prompt
|
||
|
|
library_name: transformers
|
||
|
|
license: llama3.2
|
||
|
|
tags:
|
||
|
|
- llama-3
|
||
|
|
- llama
|
||
|
|
- meta
|
||
|
|
- facebook
|
||
|
|
- unsloth
|
||
|
|
- transformers
|
||
|
|
- flux
|
||
|
|
- prompts
|
||
|
|
---
|
||
|
|
# LLM 3.2 Flux Prompt
|
||
|
|
|
||
|
|
This model is an advanced language model fine-tuned for generating high-quality image prompts, particularly optimized for use with text-to-image models like Flux.
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
## Model Details
|
||
|
|
|
||
|
|
- **Base Model**: Llama-3.2 3B
|
||
|
|
- **Fine-tuning**: Custom dataset focused on image prompt generation
|
||
|
|
- **Purpose**: Generate nuanced and precise prompts for text-to-image models
|
||
|
|
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
||
|
|
## Key Features
|
||
|
|
|
||
|
|
1. **Enhanced Data Accuracy**
|
||
|
|
- Curated, high-quality dataset
|
||
|
|
- Rigorous data cleaning methods
|
||
|
|
- Diverse range of prompt styles and topics
|
||
|
|
|
||
|
|
2. **Optimized Training**
|
||
|
|
- Fine-tuned parameters for improved performance
|
||
|
|
- Achieves more nuanced and precise prompt generation
|
||
|
|
|
||
|
|
3. **Custom ComfyUI Node**
|
||
|
|
- Enables seamless integration with text-to-image models
|
||
|
|
|
||
|
|
## Use Cases
|
||
|
|
|
||
|
|
- AI-assisted creative writing
|
||
|
|
- Generating prompts for digital art creation
|
||
|
|
- Enhancing text-to-image model inputs
|
||
|
|
|
||
|
|
## Resources
|
||
|
|
|
||
|
|
- **Hugging Face**: [ABDALLALSWAITI/llm_3_2_flux_prompt](https://huggingface.co/ABDALLALSWAITI/llm_3_2_flux_prompt)
|
||
|
|
- **Ollama Hub**: [abedalswaity7/flux-prompt](https://ollama.com/abedalswaity7/flux-prompt)
|
||
|
|
- **GitHub**: [ComfyUI-OllamaGemini](https://github.com/al-swaiti/ComfyUI-OllamaGemini)
|
||
|
|
|
||
|
|
## Tags
|
||
|
|
|
||
|
|
#AIArt #MachineLearning #NLP #ComputerVision #AIInnovation #TechDevelopment #FluxDev
|
||
|
|
|
||
|
|
---
|
||
|
|
|
||
|
|
This project aims to push the boundaries of AI-assisted creativity by generating more effective, nuanced prompts for models like Flux. We welcome collaboration and feedback from the AI community!
|