Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[ppdiffusers] Add FastDeploy+PaddleLite more devices support #4042

Merged
merged 3 commits into from
Dec 9, 2022

Conversation

shentanyue
Copy link
Contributor

PR types

New features

PR changes

Others

Description

在ppdiffusers增加FastDeploy对PaddleLite集成设备的支持

@paddle-bot
Copy link

paddle-bot bot commented Dec 7, 2022

Thanks for your contribution!

timestep=np.array([t], dtype=np.int64),
encoder_hidden_states=text_embeddings.astype(np.float32),
encoder_embedding=text_embeddings.astype(np.float32),
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

stable-diffusion-v1-4和stable-diffusion-v1-5 的输入名都是latent_input/timestep/encoder_embedding

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

现在改名与HF一致,stable-diffusion-v1-4和stable-diffusion-v1-5可以使用现在的代码重新导出个新的

@@ -42,7 +42,8 @@ python text_to_img_infer.py --model_dir stable-diffusion-v1-5/ --scheduler "eule
|----------|--------------|
| --model_dir | 导出后模型的目录。 |
| --model_format | 模型格式。默认为`'paddle'`,可选列表:`['paddle', 'onnx']`。 |
| --backend | 推理引擎后端。默认为`paddle`,可选列表:`['onnx_runtime', 'paddle']`,当模型格式为`onnx`时,可选列表为`['onnx_runtime']`。 |
| --backend | 推理引擎后端。默认为`paddle`,可选列表:`['onnx_runtime', 'paddle', 'paddlelite']`,当模型格式为`onnx`时,可选列表为`['onnx_runtime']`。 |
| --device | 运行设备。默认为`cpu`,可选列表:`['cpu', 'gpu', 'huawei_ascend_npu', 'kunlun_xpu']`,默认为gpu。 |

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

建议 kunlunxin_xpu

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

done

@JunnYu JunnYu self-requested a review December 8, 2022 07:32
Copy link
Member

@JunnYu JunnYu left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

timestep=np.array([t], dtype=np.int64),
encoder_hidden_states=text_embeddings.astype(np.float32),
encoder_embedding=text_embeddings.astype(np.float32),
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

现在改名与HF一致,stable-diffusion-v1-4和stable-diffusion-v1-5可以使用现在的代码重新导出个新的

@JunnYu JunnYu merged commit ba9f280 into PaddlePaddle:develop Dec 9, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants