import gradio as gr from stability_sdk import client import stability_sdk.interfaces.gooseai.generation.generation_pb2 as generation from PIL import Image import io import os import warnings from dotenv import load_dotenv # load secrets load_dotenv() SD_KEY = os.getenv("SD_KEY") HF_KEY = os.getenv("HF_KEY") USERNAME = os.getenv("USERNAME") PASS = os.getenv("PASS") # set up dataset writer hf_writer_gen = gr.HuggingFaceDatasetSaver(HF_KEY, "helms/master-thesis-generated-images", private=True, separate_dirs=False) def infer(prompt): stability_api = client.StabilityInference( key=SD_KEY, # AaPI Key reference. verbose=True, # Print debug messages. engine="stable-diffusion-xl-1024-v1-0", # Set the engine to use for generation. # Available engines: stable-diffusion-xl-1024-v1-0 stable-diffusion-xl-1024-v0-9 stable-diffusion-v1 stable-diffusion-v1-5 stable-diffusion-512-v2-0 stable-diffusion-768-v2-0 # stable-diffusion-512-v2-1 stable-diffusion-768-v2-1 stable-diffusion-xl-beta-v2-2-2 stable-inpainting-v1-0 stable-inpainting-512-v2-0 ) answers = stability_api.generate( prompt=prompt, # seed=992446758, # If a seed is provided, the resulting generated image will be deterministic. # What this means is that as long as all generation parameters remain the same, you can always recall the same image simply by generating it again. # Note: This isn't quite the case for Clip Guided generations, which we'll tackle in a future example notebook. steps=30, # Amount of inference steps performed on image generation. Defaults to 30. cfg_scale=7.0, # Influences how strongly your generation is guided to match your prompt. # Setting this value higher increases the strength in which it tries to match your prompt. # Defaults to 7.0 if not specified. width=1024, # Generation width, defaults to 512 if not included. height=1024, # Generation height, defaults to 512 if not included. samples=1, # Number of images to generate, defaults to 1 if not included. sampler=generation.SAMPLER_K_DPMPP_2M # Choose which sampler we want to denoise our generation with. # Defaults to k_dpmpp_2m if not specified. Clip Guidance only supports ancestral samplers. # (Available Samplers: ddim, plms, k_euler, k_euler_ancestral, k_heun, k_dpm_2, k_dpm_2_ancestral, k_dpmpp_2s_ancestral, k_lms, k_dpmpp_2m) ) for resp in answers: for artifact in resp.artifacts: if artifact.finish_reason == generation.FILTER: warnings.warn( "Your request activated the APIs safety filters and could not be processed." "Please modify the prompt and try again.") if artifact.type == generation.ARTIFACT_IMAGE: img = Image.open(io.BytesIO(artifact.binary)) return img with gr.Blocks(title="Master Thesis Image Generator") as demo: with gr.Row(): gr.HTML("""

Master Thesis Image Generator

Welcome to this demo app for the Master thesis of Fabian Helms, TU Dortmund.
Contact: fabian.helms@tu-dortmund.de

  • Please enter your name on the left hand side.
  • In the prompt field you can instruct the model on what you want to generate.
  • Generated images will be stored for research purposes only.
    • """) gr.HTML("""

    Details:
  • English prompts yield best results. Examples are shown at the bottom.
  • The generation of an image takes about 20-30 seconds.
  • Generated images are 1024x1024px in size.
  • You can see your history of generations on the left hand side. Click on an image to view it in full size.
  • Model: Stable Diffusion XL 1.0
    • """) with gr.Row(equal_height=True): with gr.Column(scale=1): user = gr.Textbox(placeholder="Please enter your name.", label="Name") inp = gr.Textbox(placeholder="Enter your prompt here.", lines=5, label="Prompt") btn_gen = gr.Button("Generate Image", variant="primary", size="lg", visible=True) with gr.Box(): gr.HTML( """

    Generated Images

    """) store = gr.Gallery(value=[], visible=True, show_share_button=False, allow_preview=False, columns=1) with gr.Column(scale=3): out = gr.Image(interactive=False, visible=True, container=True, width=1024, show_share_button=False) with gr.Row(): with gr.Accordion("See Examples:", open=False): examples = [ ["Vintage hot rod with custom flame paint job"], ["Ancient, mysterious temple in a mountain range, surrounded by misty clouds and tall peaks"], ["Glimpses of a herd of wild elephants crossing a savanna"], ["Beautiful waterfall in a lush jungle, with sunlight shining through the trees"] ] ex = gr.Examples(examples=examples, inputs=inp) def make_visible(): return gr.update(visible=True) def make_invisible(): return gr.update(visible=False) def make_inactive(): return gr.update(interactive=False) def make_active(): return gr.update(interactive=True) def add_to_gallery(img, gall): return [img] + [d['name'] for d in gall] def select_img(evt: gr.SelectData, gall): sel_img = [d['name'] for d in gall][evt.index] return sel_img hf_writer_gen.setup([user, inp, out], ".temp_gen") btn_gen.click( fn=make_inactive, outputs=btn_gen).then( fn=infer, inputs=inp, outputs=out, scroll_to_output=True).then( fn=add_to_gallery, inputs=[out, store], outputs=store).then( fn=make_active, outputs=btn_gen).then( lambda *args: hf_writer_gen.flag(args), inputs=[user, inp, out], outputs=None, preprocess=False) inp.submit( fn=make_inactive, outputs=btn_gen).then( fn=infer, inputs=inp, outputs=out, scroll_to_output=True).then( fn=add_to_gallery, inputs=[out, store], outputs=store).then( fn=make_active, outputs=btn_gen).then( lambda *args: hf_writer_gen.flag(args), inputs=[user, inp, out], outputs=None, preprocess=False) store.select(fn=select_img, inputs=store, outputs=out) demo.launch(show_api=False, auth=(USERNAME, PASS) )