SDv1.5 sd15-arthur-blip-captions model trained by Norod78 with Huggingface Diffusers train_text_to_image script

Using the screenshot images from 讗专转讜专 诇诇讗 讛拽砖专 by @GadiAleks (Both are in Hebrew)

0

The sample images above and below were generated using this smaple script

1

The dataset was a "No context Arthur screenshots with Hebrew subtitles" account. The model got the Hebrew letters nice but the words are gibberish.

Sample code


from diffusers import StableDiffusionPipeline, DPMSolverMultistepScheduler
import torch

#////////////////////////////////////////////////////////////////
guidance_scale=8.0
steps=40
width=512
height=512

prompt_suffix = ", Very detailed, clean, high quality, sharp image"
#////////////////////////////////////////////////////////////////
custom_model_id = "Norod78/sd15-arthur-blip-captions"
#////////////////////////////////////////////////////////////////
custom_model_id_str = custom_model_id.replace("/","_")
custom_model_pipe = None

def generate(prompt, file_prefix ,samples, seed):
    global base_model_pipe, custom_model_pipe

    torch.manual_seed(seed)
    prompt += prompt_suffix
    file_prefix += "Arthur"
    custom_model_images = custom_model_pipe([prompt] * samples, num_inference_steps=steps, guidance_scale=guidance_scale, height=height, width=width)["images"]
    for idx, image in enumerate(custom_model_images):
        image.save(f"{file_prefix}-{idx}-{seed}--{width}x{height}-{custom_model_id_str}.jpg")

def load():
    global base_model_pipe, custom_model_pipe
    
    scheduler = DPMSolverMultistepScheduler(
        beta_start=0.00085,
        beta_end=0.012,
        beta_schedule="scaled_linear",
        num_train_timesteps=1000,
        trained_betas=None,
        thresholding=False,
        algorithm_type="dpmsolver++",
        solver_type="midpoint",
        lower_order_final=True,
    )

    device = "cuda" if torch.cuda.is_available() else "cpu"
    dtype = torch.float16 if device == "cuda" else torch.float32
    custom_model_pipe = StableDiffusionPipeline.from_pretrained(custom_model_id, scheduler=scheduler,torch_dtype=dtype).to(device)

def main():
    load()

    generate("A livingroom", "01_LivingRoom", 4, 555)
    generate("Nicolas Cage, in \"The Minions\" movie", "02_NicolasCage", 2, 42)
    generate("Gal Gadot as wonderwoman", "03_GalGadot", 2, 42)
    generate("Gal Gadot in Avatar", "04_GalGadotAvatar", 2, 777)
    generate("Family guy taking selfies at the beach", "05_FamilyGuy", 2, 555)
    generate("Pikachu as Rick and morty, Eric Wallis", "06_PikachuRnM", 2, 777)
    generate("Pikachu as Spongebob, Eric Wallis", "07_PikachuSpongeBob", 2, 42)
    generate("An oil painting of Miss. Piggy from the muppets as the Mona Lisa", "08_MsPiggyMonaLisa", 2, 42)
    generate("Rick Sanchez from the TV show \"Rick and Morty\"", "09_RickSanchez", 2, 42)
    generate("An paiting of Southpark with rainbow", "10_Southpark", 2, 777)
    generate("A psychedelic image of Bojack Horseman", "11_Bojack", 2, 777)
    generate("A movie poster for Gravity Falls Cthulhu stories", "12_GravityFalls", 2, 777)
    generate("A vibrant oil painting portrait of She-Ra", "13_Shira", 2, 512)
#

if __name__ == '__main__':
    main()
Downloads last month
3
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.