Skip to content

various fixes to 01_stable_diffusion_introduction.ipynb #88

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

various fixes to 01_stable_diffusion_introduction.ipynb #88

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 16 additions & 6 deletions unit3/01_stable_diffusion_introduction.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -469,8 +469,8 @@
],
"source": [
"# Get the final text embeddings using the pipeline's encode_prompt function\n",
"text_embeddings = pipe._encode_prompt(\"A painting of a flooble\", device, 1, False, '')\n",
"text_embeddings.shape"
"text_embeddings = pipe.encode_prompt(\"A painting of a flooble\", device, 1, False, '')\n",
"print(\"Text embedding shape:\", text_embeddings[0].shape)"
]
},
{
Expand Down Expand Up @@ -673,7 +673,14 @@
"negative_prompt = \"zoomed in, blurry, oversaturated, warped\" #@param\n",
"\n",
"# Encode the prompt\n",
"text_embeddings = pipe._encode_prompt(prompt, device, 1, True, negative_prompt)\n",
"text_embeddings = pipe.encode_prompt(\n",
" prompt=prompt,\n",
" device=device,\n",
" num_images_per_prompt=1,\n",
" do_classifier_free_guidance=True,\n",
" negative_prompt=negative_prompt,\n",
" )\n",
"text_embeddings = torch.cat([text_embeddings[1], text_embeddings[0]])\n",
"\n",
"# Create our random starting point\n",
"latents = torch.randn((1, 4, 64, 64), device=device, generator=generator)\n",
Expand Down Expand Up @@ -704,10 +711,13 @@
"\n",
"# Decode the resulting latents into an image\n",
"with torch.no_grad():\n",
" image = pipe.decode_latents(latents.detach())\n",
" image = pipe.vae.decode(latents.detach() / pipe.vae.config.scaling_factor, return_dict=False)[0]\n",
"\n",
" image = pipe.image_processor.postprocess(image, \n",
" output_type=\"pil\",\n",
" do_denormalize=[True])[0]\n",
"# View\n",
"pipe.numpy_to_pil(image)[0]"
"display(image)"
]
},
{
Expand Down Expand Up @@ -857,7 +867,7 @@
"outputs": [],
"source": [
"# Load the inpainting pipeline (requires a suitable inpainting model)\n",
"pipe = StableDiffusionInpaintPipeline.from_pretrained(\"runwayml/stable-diffusion-inpainting\")\n",
"pipe = StableDiffusionInpaintPipeline.from_pretrained(\"stabilityai/stable-diffusion-2-inpainting\")\n",
"pipe = pipe.to(device)"
]
},
Expand Down