import gradio as gr import torch from torch import autocast from kandinsky2 import get_kandinsky2 #model_id = "hakurei/waifu-diffusion" model = get_kandinsky2('cuda', task_type='text2img') #torch.backends.cudnn.benchmark = True def infer(prompt): images = model.generate_text2img('A teddy bear на красной площади', batch_size=4, h=512, w=512, num_steps=75, denoised_type='dynamic_threshold', dynamic_threshold_v=99.5, sampler='ddim_sampler', ddim_eta=0.05, guidance_scale=10) return images css = """ .gradio-container { font-family: 'IBM Plex Sans', sans-serif; } .gr-button { color: white; border-color: black; background: black; } input[type='range'] { accent-color: black; } .dark input[type='range'] { accent-color: #dfdfdf; } .container { max-width: 730px; margin: auto; padding-top: 1.5rem; } #gallery { min-height: 22rem; margin-bottom: 15px; margin-left: auto; margin-right: auto; border-bottom-right-radius: .5rem !important; border-bottom-left-radius: .5rem !important; } #gallery>div>.h-full { min-height: 20rem; } .details:hover { text-decoration: underline; } .gr-button { white-space: nowrap; } .gr-button:focus { border-color: rgb(147 197 253 / var(--tw-border-opacity)); outline: none; box-shadow: var(--tw-ring-offset-shadow), var(--tw-ring-shadow), var(--tw-shadow, 0 0 #0000); --tw-border-opacity: 1; --tw-ring-offset-shadow: var(--tw-ring-inset) 0 0 0 var(--tw-ring-offset-width) var(--tw-ring-offset-color); --tw-ring-shadow: var(--tw-ring-inset) 0 0 0 calc(3px var(--tw-ring-offset-width)) var(--tw-ring-color); --tw-ring-color: rgb(191 219 254 / var(--tw-ring-opacity)); --tw-ring-opacity: .5; } #advanced-btn { font-size: .7rem !important; line-height: 19px; margin-top: 12px; margin-bottom: 12px; padding: 2px 8px; border-radius: 14px !important; } #advanced-options { display: none; margin-bottom: 20px; } .footer { margin-bottom: 45px; margin-top: 35px; text-align: center; border-bottom: 1px solid #e5e5e5; } .footer>p { font-size: .8rem; display: inline-block; padding: 0 10px; transform: translateY(10px); background: white; } .dark .footer { border-color: #303030; } .dark .footer>p { background: #0b0f19; } .acknowledgments h4{ margin: 1.25em 0 .25em 0; font-weight: bold; font-size: 115%; } #container-advanced-btns{ display: flex; flex-wrap: wrap; justify-content: space-between; align-items: center; } .animate-spin { animation: spin 1s linear infinite; } @keyframes spin { from { transform: rotate(0deg); } to { transform: rotate(360deg); } } #share-btn-container { display: flex; padding-left: 0.5rem !important; padding-right: 0.5rem !important; background-color: #000000; justify-content: center; align-items: center; border-radius: 9999px !important; width: 13rem; } #share-btn { all: initial; color: #ffffff;font-weight: 600; cursor:pointer; font-family: 'IBM Plex Sans', sans-serif; margin-left: 0.5rem !important; padding-top: 0.25rem !important; padding-bottom: 0.25rem !important; } #share-btn * { all: unset; } .gr-form{ flex: 1 1 50%; border-top-right-radius: 0; border-bottom-right-radius: 0; } #prompt-container{ gap: 0; } #generated_id{ min-height: 700px } """ block = gr.Blocks(css=css) examples = [ [ 'Красная площадь' ], [ 'Thinking man in anime style' ], [ 'אבוקדו' ], ] with block as demo: gr.HTML( """

Kandinskiy2.0 Demo

# Kandinsky 2.0 [![Framework: PyTorch](https://img.shields.io/badge/Framework-PyTorch-orange.svg)](https://pytorch.org/) [![Huggingface space](https://img.shields.io/badge/🤗-Huggingface-yello.svg)](https://huggingface.co/sberbank-ai/Kandinsky_2.0) `pip install "git+https://github.com/ai-forever/Kandinsky-2.0.git"` ## Model architecture: It is a latent diffusion model with two multilingual text encoders: * mCLIP-XLMR 560M parameters * mT5-encoder-small 146M parameters These encoders and multilingual training datasets unveil the real multilingual text-to-image generation experience! **Kandinsky 2.0** was trained on a large 1B multilingual set, including samples that we used to train Kandinsky. In terms of diffusion architecture Kandinsky 2.0 implements UNet with 1.2B parameters. **Kandinsky 2.0** architecture overview:

""" ) with gr.Group(): with gr.Box(): with gr.Row().style(mobile_collapse=False, equal_height=True): text = gr.Textbox( label="Enter your prompt", show_label=False, max_lines=1 ).style( border=(True, False, True, True), rounded=(True, False, False, True), container=False, ) btn = gr.Button("Run").style( margin=False, rounded=(False, True, True, False), ) gallery = gr.Gallery(label="Generated images", show_label=False, elem_id="generated_id").style( grid=[2], height="auto" ) ex = gr.Examples(examples=examples, fn=infer, inputs=[text], outputs=gallery, cache_examples=True) ex.dataset.headers = [""] text.submit(infer, inputs=[text], outputs=gallery) btn.click(infer, inputs=[text], outputs=gallery) gr.HTML( """

Stable Diffusion model fine-tuned on 56K anime image board images by hakurei

LICENSE

The model is licensed with a CreativeML Open RAIL-M license. The authors claim no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in this license. The license forbids you from sharing any content that violates any laws, produce any harm to a person, disseminate any personal information that would be meant for harm, spread misinformation and target vulnerable groups. For the full list of restrictions please read the license

Biases and content acknowledgment

Despite how impressive being able to turn text into image is, beware to the fact that this model may output content that reinforces or exacerbates societal biases, as well as realistic faces, pornography and violence. The model was trained on the LAION-5B dataset, which scraped non-curated image-text-pairs from the internet (the exception being the removal of illegal content) and is meant for research purposes. You can read more in the model card

""" ) demo.queue(max_size=25).launch()