Bumblebee
Mix.install(
[
{:kino_bumblebee, "~> 0.5.0"},
{:exla, ">= 0.0.0"}
],
config: [nx: [default_backend: EXLA.Backend]]
)
Section
repository_id = "nitrosocke/Ghibli-Diffusion"
{:ok, tokenizer} = Bumblebee.load_tokenizer({:hf, "openai/clip-vit-large-patch14"})
{:ok, clip} = Bumblebee.load_model({:hf, repository_id, subdir: "text_encoder"})
{:ok, unet} = Bumblebee.load_model({:hf, repository_id, subdir: "unet"})
{:ok, vae} =
Bumblebee.load_model({:hf, repository_id, subdir: "vae"}, architecture: :decoder)
{: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"})
serving =
Bumblebee.Diffusion.StableDiffusion.text_to_image(clip, unet, vae, tokenizer, scheduler,
num_steps: 20,
num_images_per_prompt: 1,
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: "ghibli style numbat in forest")
seed_input = Kino.Input.number("Seed")
form = Kino.Control.form([text: text_input, seed: seed_input], submit: "Run")
frame = Kino.Frame.new()
Kino.listen(form, fn %{data: %{text: text, seed: seed}} ->
Kino.Frame.render(frame, Kino.Text.new("Running..."))
output = Nx.Serving.run(serving, %{prompt: text, seed: seed})
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)
|===============================================================| 100% (2.22 MB)
|=============================================================| 100% (492.30 MB)
|============================================================| 100% (3438.36 MB)
|=============================================================| 100% (334.71 MB)
|============================================================| 100% (1216.06 MB)