Windows installation (Watch my youtube video here for more info: )
git lfs install git clone https://huggingface.co/Aitrepreneur/FLUX-Prompt-Generator
Inside the FLUX-Prompt-Generator create a new virtual env python -m venv env env\Scripts\activate
Install the requirements pip install -r requirements.txt
Then run the application python app.py
Inside the app.py file, On line 337: self.groq_client = Groq(api_key="YOUR-GROQ-API-KEY") replace YOUR-GROQ-API-KEY by your API GROQ Key if you wanna use Groq for the text generation.
IF YOU WANT TO USE EVERYTHING LOCALLY:
- Download and install ollama: https://ollama.com/
- Once Ollama is running in the background, download the Llama 3 8B model by running this command in a new cmd window: ollama run llama3
- Once the llama 3 8B model is donwloaded go in the FLux prompter Webui, check the "Use Ollama (local)" checkbox and you are good to go
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model's library.