A Stable Diffusion model fine-tuned on African fashion data to generate culturally relevant fashion images — part of the InFashAI initiative to create more inclusive and diverse AI models.
Standard generative models tend toward Western fashion styles. By fine-tuning Stable Diffusion on nearly 100,000 African fashion images from Afrikréa, we created a model that understands and generates culturally authentic African clothing — from wax prints to kente fabrics.
From data curation to image generation in three steps.
Cleaned and standardized ~100K images from Afrikréa with prompts covering clothing type, material, fabric, color, and gender.
Fine-tuned Stable Diffusion v1.4 on the curated dataset, producing 5 checkpoints at 20K, 40K, 60K, 80K, and final training steps.
Generate African fashion images from text prompts with culturally specific attributes like wax, ankara, kente, and vlisco fabrics.
The fine-tuned model outperforms the base Stable Diffusion in areas specific to African fashion.
Accurately represents wax, kente, ankara, and vlisco fabrics that the base model misses.
Captures accessories like cowries and traditional ornaments omitted by standard models.
Generates proper mid-length cloths, boubous, and other African garment types from prompts.
Produces authentic African patterns and prints rather than defaulting to Western styles.
Built on proven generative AI architecture with accessible hardware requirements.
Stable Diffusion v1.4 from CompVis — a latent text-to-image diffusion model.
~100,000 African fashion images with curated text prompts from Afrikréa platform.
96K max training steps, 512px resolution, FP16 mixed precision, 30 GB VRAM.
Only 8 GB VRAM required. 5 checkpoints available for different quality trade-offs.
Made possible through collaboration with leading organizations in research and African fashion.