Buckets:
| # 文本引导的深度图到图像生成 | |
| [StableDiffusionDepth2ImgPipeline](/docs/diffusers/v0.43.0/zh/api/pipelines/stable_diffusion/depth2img#diffusers.StableDiffusionDepth2ImgPipeline) 允许你传入文本提示词和初始图像，以作为生成新图像的条件。此外，你还可以传入 `depth_map` 来保留图像结构。如果未提供 `depth_map`，该流水线会通过集成的 [深度估计模型](https://github.com/isl-org/MiDaS) 自动预测深度。 | |
| 首先，创建一个 [StableDiffusionDepth2ImgPipeline](/docs/diffusers/v0.43.0/zh/api/pipelines/stable_diffusion/depth2img#diffusers.StableDiffusionDepth2ImgPipeline) 的实例： | |
| ```python | |
| import torch | |
| from diffusers import StableDiffusionDepth2ImgPipeline | |
| from diffusers.utils import load_image, make_image_grid | |
| pipeline = StableDiffusionDepth2ImgPipeline.from_pretrained( | |
| "stabilityai/stable-diffusion-2-depth", | |
| dtype=torch.float16, | |
| use_safetensors=True, | |
| ).to("cuda") # or "mps", "xpu", "cpu" | |
| ``` | |
| 现在将您的提示词传递给 pipeline。您还可以传入 `negative_prompt`，以防止某些词语影响图像的生成方式： | |
| ```python | |
| url = "http://images.cocodataset.org/val2017/000000039769.jpg" | |
| init_image = load_image(url) | |
| prompt = "two tigers" | |
| negative_prompt = "bad, deformed, ugly, bad anatomy" | |
| image = pipeline(prompt=prompt, image=init_image, negative_prompt=negative_prompt, strength=0.7).images[0] | |
| make_image_grid([init_image, image], rows=1, cols=2) | |
| ``` | |
| | 输入 | 输出 | | |
| |---------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------| | |
| | | | | |
Xet Storage Details
- Size:
- 1.92 kB
- Xet hash:
- 9482297f8bc877c68e0f31984927465b3127750dbc837bd347d2c87922331162
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.