Restructure model card, embed benchmark grids, fix citation year

c5b47ca verified 5 days ago

3.49 kB

license: apache-2.0
tags:
  - text-to-image
  - flux
  - african
  - nigerian
  - afrivision
language:
  - en
  - yo
  - ha
  - ig
  - pcm
pipeline_tag: text-to-image

AfriVision-Base

AfriVision-Base is a standalone text-to-image model fine-tuned from black-forest-labs/FLUX.2-klein-base-4B on AfriVision-30K, a curated dataset of African and Nigerian cultural imagery.

Developed by Axiveri AI Research.

Model Details


Base model	FLUX.2-klein-base-4B (4B param, undistilled diffusion transformer)
Task	Text-to-image generation
Dataset	AfriVision-30K (14,472 records after CLIP filtering)
Cultures covered	Yoruba, Hausa, Igbo, Nigerian Pidgin, Nigerian English
Training steps	~3,700
Resolution	768x768
LoRA rank / alpha	16 / 16
Trigger word	`AFRVS`

Usage

from diffusers import Flux2KleinPipeline
import torch

pipe = Flux2KleinPipeline.from_pretrained(
    "Axiveri/AfriVision-Base",
    torch_dtype=torch.bfloat16,
).to("cuda")

image = pipe(
    "AFRVS a Yoruba bride in traditional iro and buba at a Lagos wedding",
    num_inference_steps=28,
    guidance_scale=3.5,
).images[0]

image.save("afrivision_output.png")

Trigger Word

Include AFRVS at the start of your prompt to activate the African cultural generation style. Every training caption was prefixed with AFRVS, so the model reliably associates that token with the learned style; omitting it produces closer-to-base-model behavior.

With trigger	Without trigger
`AFRVS a Hausa man in traditional babban riga`	`a Hausa man in traditional babban riga`
Strong Nigerian cultural rendering	Closer to generic base model output

Benchmark

10 prompts spanning Yoruba, Hausa, Igbo, Pidgin, and general Nigerian contexts, each rendered three ways: base model (no LoRA), AfriVision-Base without the trigger, and AfriVision-Base with AFRVS. Same seed and sampler settings across all three for a direct comparison.

Culture	Prompt	Comparison grid
Yoruba	`a Yoruba bride in traditional iro and buba at a Lagos wedding`	grid
Yoruba	`a Yoruba grandmother weaving aso-oke in Oshogbo`	grid
Hausa	`a Hausa man in traditional babban riga`	grid
Hausa	`an Eid celebration in Kano`	grid
Igbo	`an Igbo masquerade festival in Enugu`	grid
Igbo	`a New Yam Festival celebration in a village square`	grid
General	`a Nigerian market scene at dawn`	grid
General	`Lagos waterfront at sunset`	grid
Pidgin	`a Nigerian Pidgin street food vendor frying akara`	grid
General	`a Nigerian family gathered for Sunday lunch`	grid

Full manifest (prompts, seeds, sampler settings, image paths): benchmark/benchmark_manifest.json

Citation

@misc{afrivision2026,
  author = {Emmanuel Ariyo},
  title = {AfriVision-Base: Nigerian Cultural Image Generation},
  year = {2026},
  publisher = {Axiveri AI Research},
  url = {https://huggingface.co/Axiveri/AfriVision-Base}
}