Other · Text-to-Image
Pitaya.Redmond
Generalist SDXL 0.9 fine-tune for realistic and artistic images across diverse themes. ~700k steps, trained with Redmond.AI GPU. Gated access under SDXL Rese…
About this model
Pitaya.Redmond is a generalist text-to-image model fine-tuned on Stable Diffusion XL 0.9, developed with GPU compute provided by Redmond.AI. The model was trained for approximately 700,000 steps and handles a variety of subjects — realistic scenes, artistic styles, cars, people — making it a versatile base. The author notes it is a modest improvement over the base SDXL 0.9 model and publishes it as a concept to validate training settings. The model follows the SDXL 0.9 Research License (non-commercial research only, gated access requiring application). Available on Hugging Face at artificialguybr/pitaya.
Project signals
- 1 Hugging Face likes