Ir para o conteúdo
ModelListadosExterno
Baixar

Pai Diffusion General Large Zh ControlNet Depth

我们开源了适配模型 alibaba-pai/pai-diffusion-general-large-zh 的 ControlNet,输入图像的 Depth 特征,进行可控的生成。

TipoControlNetVersãodiffusion_pytorch_modelBnota

Fonte do modelo

Tipo
ControlNet
Tamanho do arquivo
1,35 GB
Versão
vdiffusion_pytorch_model
Atualizado
8 de out. de 2026
Downloads
6
Fonte
Hugging Face

Descrição da fonte

Chinese Latent Diffusion Model

我们开源了适配模型 alibaba-pai/pai-diffusion-general-large-zh 的 ControlNet,输入图像的 Depth 特征,进行可控的生成。

from diffusers import StableDiffusionControlNetPipeline, ControlNetModel


controlnet_id = "alibaba-pai/pai-diffusion-general-large-zh-controlnet-depth"
controlnet = ControlNetModel.from_pretrained(controlnet_id)
model_id = "alibaba-pai/pai-diffusion-general-large-zh"
pipe = StableDiffusionControlNetPipeline.from_pretrained(model_id, controlnet=controlnet)
pipe = pipe.to("cuda")

image = Image.open("depth_image.png")
prompt = "雪地上的帐篷"
image = pipe(prompt, image).images[0]
image.save("result.png")

Fontes

1 fonte
Hugging FacePrimárioVersão 1db06e3190dcf4944ae17f249d3f0ae497662d6b
huggingface.co/alibaba-pai/pai-diffusion-general-large-zh-controlnet-depth/tree/1db06e3190dcf4944ae17f249d3f0ae497662d6b

Verificado 8 de out.

Artefatos de modelo

1 artefato

diffusion_pytorch_model.bin

bin · 1,35 GB · SHA-256 f57d12cc0360…57c2 · Hugging Face

Baixar

Trechos de fonte

3 trechos

--- license: apache-2.0 tags: - pytorch - diffusers - text-to-image --- # Chinese Latent Diffusion Model 我们开源了适配模型 `alibaba-pai/pai-diffusion-general-large-zh` 的 ControlNet,输入图像的 Depth 特征,进行可控的生成。 * Github: [EasyNLP](https://github.com/alibaba/EasyNLP) ```python from diffusers import StableDiffusionControlNetPipeline, ControlNetModel controlnet_id = "alibaba-pai/pai-diffusion-general-large-zh-controlnet-depth" controlnet = ControlNetModel.from_pretrained(controlnet_id) model_id = "alibaba-pai/pai-diffusion-general-large-zh" pipe = StableDiffusionControlNetPipeline.from_pretrained(model_id, controlnet=controlnet) pipe = pipe.to("cuda") image = Image.open("depth_image.png") prompt = "雪地上的帐篷" image = pipe(prompt, image).images[0] image.save("result.png") ```

Source context: 6 downloads · 0 likes · Pipeline text-to-image · Library diffusers · Repo alibaba-pai/pai-diffusion-general-large-zh-controlnet-depth

Source context: 0 downloads · 0 likes · Pipeline text-to-image · Library diffusers · Repo alibaba-pai/pai-diffusion-general-large-zh-controlnet-depth