datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
diffusers-pr
Diffusers PR Dataset
Normalized snapshots of issues, pull requests, comments, reviews, and linkage data from huggingface/diffusers.
Files:
issues.parquet
pull_requests.parquet
comments.parquet
issue_comments.parquet (derived view of issue discussion comments)
pr_comments.parquet (derived view of pull request discussion comments)
reviews.parquet
pr_files.parquet
pr_diffs.parquet
review_comments.parquet
links.parquet
events.parquet
new_contributors.parquet… See the full description on the dataset page: https://huggingface.co/datasets/evalstate/diffusers-pr.diffusers-metadatapokemon-gpt4-captions
Dataset Card for "pokemon-gpt4-captions"
This dataset is just lambdalabs/pokemon-blip-captions but the captions come from GPT-4 (Turbo).
Code used to generate the captions:
import base64
from io import BytesIO
import requests
from PIL import Image
def encode_image(image):
buffered = BytesIO()
image.save(buffered, format="JPEG")
img_str = base64.b64encode(buffered.getvalue())
returnimg_str.decode("utf-8")
def create_payload(image_string):
payload = {… See the full description on the dataset page: https://huggingface.co/datasets/diffusers/pokemon-gpt4-captions.diffusers-dependents
diffusers metrics
This dataset contains metrics about the huggingface/diffusers package.
Number of repositories in the dataset: 160
Number of packages in the dataset: 2
Package dependents
This contains the data available in the used-by
tab on GitHub.
Package & Repository star count
This section shows the package and repository star count, individually.
Package
Repository
There are 0 packages that have more than 1000 stars.
There are 3 repositories… See the full description on the dataset page: https://huggingface.co/datasets/open-source-metrics/diffusers-dependents.instructpix2pix-clip-filtered-upscaledmvp-certificateseye_rolling
Eye Rolling Image-video dataset
containing pairs of face images with corresponding video of the person rolling their eyes
images were downloaded from Unsplash
videos were created using LivePortrait
diffusers-qa-chatbot-artifactsbenchmarks
Welcome to 🤗 Diffusers Benchmarks!
This is dataset where we keep track of the inference latency and memory information of the core models in the diffusers library.
Currently, the core models are:
Flux
Wan
LTX
SDXL
Note that we will continue to extend this list based on their usage.
You can analyze the results in this demo.
[!IMPORTANT]
Instead of benchmarking the entire diffusion pipelines, we only benchmark the forward passes
of the diffusion networks under different settings… See the full description on the dataset page: https://huggingface.co/datasets/diffusers/benchmarks.ShotDEAD-v0
ShotDEAD-v0
Shot Directors Environment Actors Dataset
This dataset covers environment and contains still frames from a variety of films. The tags describe visual attributes of each image, including color, lighting, and composition.
Dataset Structure
Example Tags
Each image is labeled with the following categories:
COLOR
Indicates the dominant color palette in the image:
Mixed
Saturated
Desaturated
Warm
Red
Blue
Cyan
LIGHTING
Describes… See the full description on the dataset page: https://huggingface.co/datasets/diffusers/ShotDEAD-v0.tuxemonTuxemon Dataset
This dataset contains images of mosnters from The Tuxemon Project - an open source effort for a monster catching game.
These image-caption pairs can be used for text-to-image tuning & benchmarking.
All images in this dataset were downloaded from https://wiki.tuxemon.org/Category:Monster
Some images were upscaled using SDx4 upscaler & HiDiffusion
Captions generated with
BLIP-large (some were manually modified)
GPT-4 Turbo
[!TIP]
One can use the mix of captions provided in the… See the full description on the dataset page: https://huggingface.co/datasets/diffusers/tuxemon.sdxl-1.0
Dataset Card for "sdxl-1.0"
Dataset was generated using the code below:
import torch
from datasets import Dataset, Features
from datasets import Image as ImageFeature
from datasets import Value, load_dataset
from diffusers import DDIMScheduler, DiffusionPipeline
import PIL
def main():
print("Loading dataset...")
parti_prompts = load_dataset("nateraw/parti-prompts", split="train")
print("Loading pipeline...")
ckpt_id = "stabilityai/stable-diffusion-xl-base-1.0"… See the full description on the dataset page: https://huggingface.co/datasets/diffusers-parti-prompts/sdxl-1.0.sd-v1-5
Images of Parti Prompts for "sd-v1-5"
Code that was used to get the results:
from diffusers import DiffusionPipeline, DDIMScheduler
import torch
import PIL
pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, safety_checker=None)
pipe.to("cuda")
pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config)
prompt = "" # a parti prompt
generator = torch.Generator("cuda").manual_seed(0)
image = pipe(prompt, generator=generator… See the full description on the dataset page: https://huggingface.co/datasets/diffusers-parti-prompts/sd-v1-5.example-dataset
ORB Transformation Applied on diffusiondb Dataset
This dataset consists of images, captions and images that are transformed to extract features using ORB transform.
You can find the original dataset here.
An example sample is below:
Caption: "spider - man, cinematic, photography "
Image:
Transformation:
canny_diffusiondb
Canny DiffusionDB
This dataset is the DiffusionDB dataset that is transformed using Canny transformation.
You can see samples below 👇
Sample:
Original Image:
Transformed Image:
Caption:
"a small wheat field beside a forest, studio lighting, golden ratio, details, masterpiece, fine art, intricate, decadent, ornate, highly detailed, digital painting, octane render, ray tracing reflections, 8 k, featured, by claude monet and vincent van gogh "Below you can find a small script used… See the full description on the dataset page: https://huggingface.co/datasets/jax-diffusers-event/canny_diffusiondb.sdxl-0.9
Dataset Card for "sdxl-0.9"
Dataset was generated using the code below:
import torch
from datasets import Dataset, Features
from datasets import Image as ImageFeature
from datasets import Value, load_dataset
from diffusers import DDIMScheduler, DiffusionPipeline
import PIL
def main():
print("Loading dataset...")
parti_prompts = load_dataset("nateraw/parti-prompts", split="train")
print("Loading pipeline...")
ckpt_id = "stabilityai/stable-diffusion-xl-base-0.9"… See the full description on the dataset page: https://huggingface.co/datasets/diffusers-parti-prompts/sdxl-0.9.Image2PositionColor_v3_diffuserskandinsky-2-2
Dataset Card for "kandinsky-2-2"
The dataset was generated using the code below:
import PIL
import torch
from datasets import Dataset, Features
from datasets import Image as ImageFeature
from datasets import Value, load_dataset
from diffusers import DiffusionPipeline
def main():
print("Loading dataset...")
parti_prompts = load_dataset("nateraw/parti-prompts", split="train")
print("Loading pipeline...")
pipe_prior = DiffusionPipeline.from_pretrained(… See the full description on the dataset page: https://huggingface.co/datasets/diffusers-parti-prompts/kandinsky-2-2.muse512
Dataset Card for "muse_512"
```py
from PIL import Image
import torch
from muse import PipelineMuse, MaskGiTUViT
from datasets import Dataset, Features
from datasets import Image as ImageFeature
from datasets import Value, load_dataset
device = "cuda" if torch.cuda.is_available() else "cpu"
pipe = PipelineMuse.from_pretrained(
transformer_path="valhalla/research-run",
text_encoder_path="openMUSE/clip-vit-large-patch14-text-enc"… See the full description on the dataset page: https://huggingface.co/datasets/diffusers-parti-prompts/muse512.transformers-diffusers-docs-chunkedsdxl-1.0-refiner
Dataset Card for "sdxl-1.0-refiner"
Dataset was generated using the code below:
import torch
from datasets import Dataset, Features
from datasets import Image as ImageFeature
from datasets import Value, load_dataset
from diffusers import DDIMScheduler, DiffusionPipeline
import PIL
def main():
print("Loading dataset...")
parti_prompts = load_dataset("nateraw/parti-prompts", split="train")
print("Loading pipeline...")
ckpt_id =… See the full description on the dataset page: https://huggingface.co/datasets/diffusers-parti-prompts/sdxl-1.0-refiner.sd-v2.1
Images of Parti Prompts for "sd-v2.1"
Code that was used to get the results:
from diffusers import DiffusionPipeline, DDIMScheduler
import torch
import PIL
pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-2-1", torch_dtype=torch.float16, safety_checker=None)
pipe.to("cuda")
pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config)
prompt = "" # a parti prompt
generator = torch.Generator("cuda").manual_seed(0)
image = pipe(prompt, generator=generator… See the full description on the dataset page: https://huggingface.co/datasets/diffusers-parti-prompts/sd-v2.1.if-v-1.0
Images of Parti Prompts for "if-v-1.0"
Code that was used to get the results:
from diffusers import DiffusionPipeline
import torch
pipe_low = DiffusionPipeline.from_pretrained("DeepFloyd/IF-I-XL-v1.0", safety_checker=None, watermarker=None, torch_dtype=torch.float16, variant="fp16")
pipe_low.enable_model_cpu_offload()
pipe_up = DiffusionPipeline.from_pretrained("DeepFloyd/IF-II-L-v1.0", safety_checker=None, watermarker=None, text_encoder=pipe_low.text_encoder… See the full description on the dataset page: https://huggingface.co/datasets/diffusers-parti-prompts/if-v-1.0.pokemon-llava-captions
Dataset Card for "pokemon-llava-captions"
This dataset is just lambdalabs/pokemon-blip-captions but the captions come
from the LLaVA model.
Refer to the notebook that generated this dataset.
test_failureskarlo-v1
Images of Parti Prompts for "karlo-v1"
Code that was used to get the results:
from diffusers import DiffusionPipeline
import torch
pipe = DiffusionPipeline.from_pretrained("kakaobrain/karlo-v1-alpha", torch_dtype=torch.float16)
pipe.to("cuda")
prompt = "" # a parti prompt
generator = torch.Generator("cuda").manual_seed(0)
image = pipe(prompt, prior_num_inference_steps=50, decoder_num_inference_steps=100, generator=generator).images[0]
transformers-diffusers-docs-rawsdxl-0.9-refiner
Dataset Card for "sdxl-0.9-refiner"
Dataset was generated using the code below:
import torch
from datasets import Dataset, Features
from datasets import Image as ImageFeature
from datasets import Value, load_dataset
from diffusers import DDIMScheduler, DiffusionPipeline
import PIL
def main():
print("Loading dataset...")
parti_prompts = load_dataset("nateraw/parti-prompts", split="train")
print("Loading pipeline...")
ckpt_id =… See the full description on the dataset page: https://huggingface.co/datasets/diffusers-parti-prompts/sdxl-0.9-refiner.muse256from PIL import Image
import torch
from muse import PipelineMuse, MaskGiTUViT
from datasets import Dataset, Features
from datasets import Image as ImageFeature
from datasets import Value, load_dataset
device = "cuda" if torch.cuda.is_available() else "cpu"
pipe = PipelineMuse.from_pretrained(
transformer_path="valhalla/research-run",
text_encoder_path="openMUSE/clip-vit-large-patch14-text-enc",
vae_path="openMUSE/vqgan-f16-8192-laion",
).to(device)
# pipe.transformer =… See the full description on the dataset page: https://huggingface.co/datasets/diffusers-parti-prompts/muse256.diffusers-quantization-benchmarks