briaai / nfl_HD

About

this is the modle currently (12/05/2024) used in our production pipeline.

Training process

We started from the briaai/BRIA-2.2-HD model (starting from checkpoint 1223000) and finetune it.

Dataset

The dataset that was use to train this modle was is located in s3://fox-raw-data/images_hd/ the images are at size (1088*2048) and with grey bg color (128,128,128) the caption for the images was: "An illustration of the NFL player: \"{player_name}\" from the team: \"{team_name}\"."

Training parameters

the training script can be found on spring/Infra/project_x/stable_xl/accelerate_launch_prod_xl_us_west.py

lr: 2e-05
batch: 4
accumulate: 2

Evaluation

from diffusers import StableDiffusionXLPipeline
import torch

pipe = StableDiffusionXLPipeline.from_pretrained("briaai/nfl_HD", torch_dtype=torch.float16, use_safetensors=True)
pipe.to("cuda")
player_name = "Gal Davidi"
team_name = "Indianapolis Colts"

prompt = "An illustration of the NFL player: \"{player_name}\" from the team: \"{team_name}\"."
negative_prompt = "Logo,Watermark,Text,Ugly,Morbid,Extra fingers,Poorly drawn hands,Mutation,Blurry,Extra limbs,Gross proportions,Missing arms,Mutated hands,Long neck,Duplicate,Mutilated,Mutilated hands,Poorly drawn face,Deformed,Bad anatomy,Cloned face,Malformed limbs,Missing legs,Too many fingers"

images = pipe(prompt=prompt, negative_prompt=negative_prompt, height=2048, width=1088).images[0]