Skip to content

Update diffusers default snippets to be complete. #907

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

Merged
Vaibhavs10 merged 6 commits into from
Sep 18, 2024
Merged

Update diffusers default snippets to be complete. #907

Changes from 2 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
d05764b
Update diffusers default snippets to be complete.
Vaibhavs10 Sep 17, 2024
84ededa
Lint.
Vaibhavs10 Sep 17, 2024
1d055b4
pnpm format
mishig25 Sep 17, 2024
57a4dac
Suggestions from review.
Vaibhavs10 Sep 17, 2024
5ea7abb
fkn lint.
Vaibhavs10 Sep 17, 2024
2bf47fa
Merge branch 'main' into vb/fix-diffusers-snippet
Vaibhavs10 Sep 18, 2024
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
14 changes: 10 additions & 4 deletions packages/tasks/src/model-libraries-snippets.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -132,7 +132,10 @@ depth = model.infer_image(raw_img) # HxW raw depth map in numpy
const diffusers_default = (model: ModelData) => [
`from diffusers import DiffusionPipeline

pipeline = DiffusionPipeline.from_pretrained("${model.id}")`,
pipeline = DiffusionPipeline.from_pretrained("${model.id}")

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipeline(prompt).images[0]`,
];

const diffusers_controlnet = (model: ModelData) => [
Expand All @@ -148,7 +151,10 @@ const diffusers_lora = (model: ModelData) => [
`from diffusers import DiffusionPipeline

pipeline = DiffusionPipeline.from_pretrained("${get_base_diffusers_model(model)}")
pipeline.load_lora_weights("${model.id}")`,
pipeline.load_lora_weights("${model.id}")

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipeline(prompt).images[0]`,
];

const diffusers_textual_inversion = (model: ModelData) => [
Expand Down Expand Up @@ -746,8 +752,8 @@ export const transformers = (model: ModelData): string[] => {
info.processor === "AutoTokenizer"
? "tokenizer"
: info.processor === "AutoFeatureExtractor"
? "extractor"
: "processor";
? "extractor"
: "processor";
autoSnippet = [
"# Load model directly",
`from transformers import ${info.processor}, ${info.auto_model}`,
Expand Down