Stable Diffusion - Modern Disney
Mix.install(
[
{:bumblebee, "~> 0.1.0"},
{:nx, "~> 0.4.1"},
{:exla, "~> 0.4.1"},
{:kino, "~> 0.8.0"},
{:kino_bumblebee, "~> 0.1.0"}
],
config: [nx: [default_backend: EXLA.Backend]]
)
Nx.global_default_backend(EXLA.Backend)
Text to image
repository_id = "nitrosocke/mo-di-diffusion"
{:ok, tokenizer} = Bumblebee.load_tokenizer({:hf, "openai/clip-vit-large-patch14"})
{:ok, clip} =
Bumblebee.load_model({:hf, repository_id, subdir: "text_encoder"},
log_params_diff: false
)
{:ok, unet} =
Bumblebee.load_model({:hf, repository_id, subdir: "unet"},
params_filename: "diffusion_pytorch_model.bin",
log_params_diff: false
)
{:ok, vae} =
Bumblebee.load_model({:hf, repository_id, subdir: "vae"},
architecture: :decoder,
params_filename: "diffusion_pytorch_model.bin",
log_params_diff: false
)
{:ok, scheduler} = Bumblebee.load_scheduler({:hf, repository_id, subdir: "scheduler"})
{:ok, featurizer} = Bumblebee.load_featurizer({:hf, repository_id, subdir: "feature_extractor"})
{:ok, safety_checker} =
Bumblebee.load_model({:hf, repository_id, subdir: "safety_checker"},
log_params_diff: false
)
serving =
Bumblebee.Diffusion.StableDiffusion.text_to_image(clip, unet, vae, tokenizer, scheduler,
num_steps: 40,
num_images_per_prompt: 4,
safety_checker: safety_checker,
safety_checker_featurizer: featurizer,
compile: [batch_size: 1, sequence_length: 50],
defn_options: [compiler: EXLA]
)
text_input = Kino.Input.textarea("Text", default: "modern disney style grumpy cat")
form = Kino.Control.form([text: text_input], submit: "Run")
frame = Kino.Frame.new()
form
|> Kino.Control.stream()
|> Kino.listen(fn %{data: %{text: text}} ->
Kino.Frame.render(frame, Kino.Markdown.new("Running..."))
output = Nx.Serving.run(serving, text)
for result <- output.results do
Kino.Image.new(result.image)
end
|> Kino.Layout.grid(columns: 2)
|> then(&Kino.Frame.render(frame, &1))
end)
Kino.Layout.grid([form, frame], boxed: true, gap: 16)