by kudzueye
Open source · 3k downloads · 126 likes
Boreal-Qwen-Image is an experimental model designed to generate images from text descriptions, leveraging advanced machine learning techniques. It stands out for its modular approach, utilizing LoRAs (Low-Rank Adaptations) to refine results, often combined to enhance the quality of the generated images. The model excels particularly in creating realistic portraits and photographic scenes, though its performance remains in a testing phase and may require manual adjustments for optimal outcomes. Its activation keyword, "photo," triggers generation in compatible workflows. Aimed at experienced users, it caters to artists and developers seeking to explore innovative visual styles while accepting a degree of unpredictability in the outputs.
🚧 Work in Progress - Experimental Model 🚧
Status: Experimental/Testing Phase You should not expect great results from these LoRAs at the moment. It often involves using them together to get best results. I may be able to merge them later on for more consistent results, but I am uncertain of how good the actual quality will be.
I recommend combining these loras together in whatever workflow you use. Have the general discrete lora set at a strength of 1.0 and the the portrait blend high rank model to something like 0.6 - 0.8.
You will need to experiment a lot to figure out the best results. I am still uncertain of the best way to work with Qwen yet and how I should approach newer versions for this style.
ComfyUI Example Workflow: https://huggingface.co/kudzueye/boreal-qwen-image/blob/main/boreal-qwen-workflow-v1.json
This model is part of ongoing research and experimentation. Description and documentation will be updated as development progresses.
You should use photo to trigger the image generation.
Download them in the Files & versions tab.