Almost-AGI-Diffusion/wuerst

---
dataset_info:
features:
- name: Prompt
dtype: string
- name: Category
dtype: string
- name: Challenge
dtype: string
- name: Note
dtype: string
- name: images
dtype: image
- name: model_name
dtype: string
- name: seed
dtype: int64
- name: upvotes
dtype: int64
splits:
- name: train
num_bytes: 19633368.0
num_examples: 219
download_size: 19625614
dataset_size: 19633368.0
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
# Wuerstchen

All images included in this dataset were voted as "Not solved" by the community in https://huggingface.co/spaces/OpenGenAI/open-parti-prompts. This means that according to the community the model did not generate an image that corresponds sufficiently enough to the prompt.

The following script was used to generate the images:

```py
import torch
from datasets import Dataset, Features
from datasets import Image as ImageFeature
from datasets import Value, load_dataset
from diffusers import AutoPipelineForText2Image

import PIL

def main():
print("Loading dataset...")
parti_prompts = load_dataset("nateraw/parti-prompts", split="train")

print("Loading pipeline...")
seed = 0

device = "cuda"
generator = torch.Generator(device).manual_seed(seed)
dtype = torch.float16

ckpt_id = "warp-diffusion/wuerstchen"

pipeline = AutoPipelineForText2Image.from_pretrained(
ckpt_id, torch_dtype=dtype
).to(device)

pipeline.prior_prior = torch.compile(pipeline.prior_prior, mode="reduce-overhead", fullgraph=True)
pipeline.decoder = torch.compile(pipeline.decoder, mode="reduce-overhead", fullgraph=True)

print("Running inference...")
main_dict = {}
for i in range(len(parti_prompts)):
sample = parti_prompts[i]
prompt = sample["Prompt"]

image = pipeline(
prompt=prompt,
height=1024,
width=1024,
prior_guidance_scale=4.0,
decoder_guidance_scale=0.0,
generator=generator,
).images[0]

image = image.resize((256, 256), resample=PIL.Image.Resampling.LANCZOS)
img_path = f"wuerstchen_{i}.png"
image.save(img_path)
main_dict.update(
{
prompt: {
"img_path": img_path,
"Category": sample["Category"],
"Challenge": sample["Challenge"],
"Note": sample["Note"],
"model_name": ckpt_id,
"seed": seed,
}
}
)

def generation_fn():
for prompt in main_dict:
prompt_entry = main_dict[prompt]
yield {
"Prompt": prompt,
"Category": prompt_entry["Category"],
"Challenge": prompt_entry["Challenge"],
"Note": prompt_entry["Note"],
"images": {"path": prompt_entry["img_path"]},
"model_name": prompt_entry["model_name"],
"seed": prompt_entry["seed"],
}

print("Preparing HF dataset...")
ds = Dataset.from_generator(
generation_fn,
features=Features(
Prompt=Value("string"),
Category=Value("string"),
Challenge=Value("string"),
Note=Value("string"),
images=ImageFeature(),
model_name=Value("string"),
seed=Value("int64"),
),
)
ds_id = "diffusers-parti-prompts/wuerstchen"
ds.push_to_hub(ds_id)

if __name__ == "__main__":
main()
```

原始信息汇总

数据集概述

数据集信息

• 特征列表:

  • Prompt: 字符串类型
  • Category: 字符串类型
  • Challenge: 字符串类型
  • Note: 字符串类型
  • images: 图像类型
  • model_name: 字符串类型
  • seed: 64位整数类型
  • upvotes: 64位整数类型

• 数据分割:

  • train:
    • 字节数: 19633368.0
    • 样本数: 219

• 数据集大小:

  • 下载大小: 19625614
  • 实际大小: 19633368.0

配置信息

• 配置名称: default
  • 数据文件:
    • 分割: train
    • 路径: data/train-*