Pixart 900m 1024 Ft V0.6

🚀 pixart-900m-1024-ft

本項目是基於 ptx0/pixart-900m-1024-ft-large 的全秩微調模型。它能夠根據輸入的文本描述生成高質量的圖像，在圖像生成領域具有廣泛的應用前景。

🚀 快速開始

你可以按照以下步驟進行推理：

import torch
from diffusers import DiffusionPipeline

model_id = 'pixart-900m-1024-ft'
prompt = 'ethnographic photography of teddy bear at a picnic, ears tucked behind a cozy hoodie looking darkly off to the stormy picnic skies'
negative_prompt = 'blurry, cropped, ugly'
pipeline = DiffusionPipeline.from_pretrained(model_id)
pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')

prompt = "ethnographic photography of teddy bear at a picnic, ears tucked behind a cozy hoodie looking darkly off to the stormy picnic skies"
negative_prompt = "blurry, cropped, ugly"

pipeline = DiffusionPipeline.from_pretrained(model_id)
pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
image = pipeline(
    prompt=prompt,
    negative_prompt='blurry, cropped, ugly',
    num_inference_steps=25,
    generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(1641421826),
    width=1152,
    height=768,
    guidance_scale=4.5,
    guidance_rescale=0.0,
).images[0]
image.save("output.png", format="PNG")

✨ 主要特性

• 基於 ptx0/pixart-900m-1024-ft-large 進行全秩微調。
• 文本編碼器未進行訓練，可複用基礎模型的文本編碼器進行推理。

📚 詳細文檔

驗證設置

• CFG: 4.5
• CFG Rescale: 0.0
• Steps: 25
• Sampler: None
• Seed: 42
• Resolutions: 1024x1024,1344x768,916x1152

注意：驗證設置不一定與訓練設置相同。

你可以在以下圖庫中找到一些示例圖像：

訓練設置

數據集

photo-concept-bucket

💻 使用示例

基礎用法

import torch
from diffusers import DiffusionPipeline

model_id = 'pixart-900m-1024-ft'
prompt = 'ethnographic photography of teddy bear at a picnic, ears tucked behind a cozy hoodie looking darkly off to the stormy picnic skies'
negative_prompt = 'blurry, cropped, ugly'
pipeline = DiffusionPipeline.from_pretrained(model_id)
pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')

prompt = "ethnographic photography of teddy bear at a picnic, ears tucked behind a cozy hoodie looking darkly off to the stormy picnic skies"
negative_prompt = "blurry, cropped, ugly"

pipeline = DiffusionPipeline.from_pretrained(model_id)
pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
image = pipeline(
    prompt=prompt,
    negative_prompt='blurry, cropped, ugly',
    num_inference_steps=25,
    generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(1641421826),
    width=1152,
    height=768,
    guidance_scale=4.5,
    guidance_rescale=0.0,
).images[0]
image.save("output.png", format="PNG")

高級用法

你可以根據需要調整 prompt、negative_prompt、num_inference_steps、width、height、guidance_scale 和 guidance_rescale 等參數，以獲得不同風格和質量的圖像。

import torch
from diffusers import DiffusionPipeline

model_id = 'pixart-900m-1024-ft'
# 自定義提示
prompt = 'A beautiful sunset over the ocean'
negative_prompt = 'ugly, blurry'
pipeline = DiffusionPipeline.from_pretrained(model_id)
pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')

image = pipeline(
    prompt=prompt,
    negative_prompt=negative_prompt,
    num_inference_steps=30,  # 增加推理步數
    generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(42),
    width=1280,  # 調整圖像寬度
    height=720,  # 調整圖像高度
    guidance_scale=5.0,  # 調整引導比例
    guidance_rescale=0.1,  # 調整引導重新縮放比例
).images[0]
image.save("custom_output.png", format="PNG")

📄 許可證

本項目採用 creativeml-openrail-m 許可證。