From 4449982f868afb0459a5006afaa5ffad5d75a92c Mon Sep 17 00:00:00 2001 From: Xiaoyu Xu Date: Thu, 7 Dec 2023 11:27:31 +0800 Subject: [PATCH 1/7] Update README.md --- README.md | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-) diff --git a/README.md b/README.md index 68aa4a73c..b3ffdbf59 100644 --- a/README.md +++ b/README.md @@ -3,7 +3,7 @@ # OneDiff -A **drop-in acceleration lib** for diffusers and other **diffusion models**. +A **drop-in acceleration lib** for **ComfyUI**, **HF diffusers**, and other diffusion models. ## Performance of OneDiff Community Edition @@ -19,21 +19,28 @@ Updated on Nov 6, 2023. > **_NOTE:_** OneDiff Enterprise Edition delivers even higher performance and second-to-none deployment flexibility. ## Features -- Acceleration for SDXL, SD2.1 and so on +- Acceleration for popular libs + - [ComfyUI](https://github.com/Oneflow-Inc/onediff/tree/main/onediff_comfy_nodes) + - [HF diffusers](https://github.com/Oneflow-Inc/onediff/tree/main/examples) + - SD Web UI(On the way) +- Acceleration for state-of-the-art Models - [SDXL](https://github.com/Oneflow-Inc/onediff/blob/main/examples/text_to_image_sdxl.py) - - [SD2.1](https://github.com/Oneflow-Inc/onediff/blob/main/examples/text_to_image.py) + - [SD1.5-2.1](https://github.com/Oneflow-Inc/onediff/blob/main/examples/text_to_image.py) - [LoRA](https://github.com/Oneflow-Inc/onediff/blob/main/examples/text_to_image_sdxl_lora.py) - [ControlNet](https://github.com/Oneflow-Inc/onediff/blob/main/examples/text_to_image_controlnet.py) - [LCM](https://github.com/Oneflow-Inc/onediff/blob/main/examples/text_to_image_lcm.py) and [LCM LoRA](https://github.com/Oneflow-Inc/onediff/blob/main/examples/text_to_image_lcm_lora_sdxl.py) - [SDXL Turbo](https://github.com/Oneflow-Inc/onediff/blob/main/examples/text_to_image_sdxl_turbo.py) -- Compile PyTorch models (like UNet) with one function - - [oneflow_compile](https://github.com/Oneflow-Inc/onediff/blob/a38c5ea475c07b4527981ec5723ccac083ed0a9c/examples/text_to_image_sdxl.py#L53) -- Enable multi-resolution input with the same compiled model - - [The Multi graph way](https://github.com/Oneflow-Inc/onediff/blob/a38c5ea475c07b4527981ec5723ccac083ed0a9c/examples/text_to_image_sdxl_save_load.py#L65) -- Save/load/change device of the compiled graph +- Support drop-in acceleration + - [ComfyUI Nodes](https://github.com/Oneflow-Inc/onediff/tree/main/onediff_comfy_nodes) + - [Acceleration with oneflow_compile](https://github.com/Oneflow-Inc/onediff/blob/a38c5ea475c07b4527981ec5723ccac083ed0a9c/examples/text_to_image_sdxl.py#L53) +- Support multi-resolution input + - [Multi-resolution input](https://github.com/Oneflow-Inc/onediff/blob/a38c5ea475c07b4527981ec5723ccac083ed0a9c/examples/text_to_image_sdxl_save_load.py#L65) +- Save/load/change device of the compiled result - [Save and Load](https://github.com/Oneflow-Inc/onediff/blob/main/examples/text_to_image_sdxl_save_load.py) - [Change device to do multi-process serving](https://github.com/Oneflow-Inc/onediff/blob/main/examples/text_to_image_sdxl_mp_load.py) + + ## Business inquiry on OneDiff Enterprise Edition If you need **unrestricted multiple resolution**, **quantization** support or any other more advanced features, please send an email to caishenghang@oneflow.org . Tell us about your **use case, deployment scale and requirements**! From 32b05bf08dc80dd008b02263a7ecf4fe0d27ad73 Mon Sep 17 00:00:00 2001 From: Xiaoyu Xu Date: Thu, 7 Dec 2023 11:36:35 +0800 Subject: [PATCH 2/7] Update README.md Co-authored-by: Shenghang Tsai --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index b3ffdbf59..f0d66d451 100644 --- a/README.md +++ b/README.md @@ -25,7 +25,7 @@ Updated on Nov 6, 2023. - SD Web UI(On the way) - Acceleration for state-of-the-art Models - [SDXL](https://github.com/Oneflow-Inc/onediff/blob/main/examples/text_to_image_sdxl.py) - - [SD1.5-2.1](https://github.com/Oneflow-Inc/onediff/blob/main/examples/text_to_image.py) + - [SD 1.5/2.1](https://github.com/Oneflow-Inc/onediff/blob/main/examples/text_to_image.py) - [LoRA](https://github.com/Oneflow-Inc/onediff/blob/main/examples/text_to_image_sdxl_lora.py) - [ControlNet](https://github.com/Oneflow-Inc/onediff/blob/main/examples/text_to_image_controlnet.py) - [LCM](https://github.com/Oneflow-Inc/onediff/blob/main/examples/text_to_image_lcm.py) and [LCM LoRA](https://github.com/Oneflow-Inc/onediff/blob/main/examples/text_to_image_lcm_lora_sdxl.py) From 357fb062e5b07c9d1b911d3dcb959ed7639ccf35 Mon Sep 17 00:00:00 2001 From: Xiaoyu Xu Date: Thu, 7 Dec 2023 11:37:13 +0800 Subject: [PATCH 3/7] Update README.md Co-authored-by: Shenghang Tsai --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index f0d66d451..116f478f3 100644 --- a/README.md +++ b/README.md @@ -21,7 +21,7 @@ Updated on Nov 6, 2023. ## Features - Acceleration for popular libs - [ComfyUI](https://github.com/Oneflow-Inc/onediff/tree/main/onediff_comfy_nodes) - - [HF diffusers](https://github.com/Oneflow-Inc/onediff/tree/main/examples) + - [HF diffusers 🤗](https://github.com/Oneflow-Inc/onediff/tree/main/examples) - SD Web UI(On the way) - Acceleration for state-of-the-art Models - [SDXL](https://github.com/Oneflow-Inc/onediff/blob/main/examples/text_to_image_sdxl.py) From 68b82836f154d939fb2cf16469fa511a35cde4aa Mon Sep 17 00:00:00 2001 From: Xiaoyu Xu Date: Thu, 7 Dec 2023 11:39:43 +0800 Subject: [PATCH 4/7] Update README.md Co-authored-by: Shenghang Tsai --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 116f478f3..00e3edaf9 100644 --- a/README.md +++ b/README.md @@ -35,7 +35,7 @@ Updated on Nov 6, 2023. - [Acceleration with oneflow_compile](https://github.com/Oneflow-Inc/onediff/blob/a38c5ea475c07b4527981ec5723ccac083ed0a9c/examples/text_to_image_sdxl.py#L53) - Support multi-resolution input - [Multi-resolution input](https://github.com/Oneflow-Inc/onediff/blob/a38c5ea475c07b4527981ec5723ccac083ed0a9c/examples/text_to_image_sdxl_save_load.py#L65) -- Save/load/change device of the compiled result +- Save/load the compiled result, deploy on different environments - [Save and Load](https://github.com/Oneflow-Inc/onediff/blob/main/examples/text_to_image_sdxl_save_load.py) - [Change device to do multi-process serving](https://github.com/Oneflow-Inc/onediff/blob/main/examples/text_to_image_sdxl_mp_load.py) From 07a51e1b252d61a57bdc0d82609f71e9af34f58f Mon Sep 17 00:00:00 2001 From: Xiaoyu Xu Date: Thu, 7 Dec 2023 11:39:53 +0800 Subject: [PATCH 5/7] Update README.md Co-authored-by: Shenghang Tsai --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 00e3edaf9..9630da4ea 100644 --- a/README.md +++ b/README.md @@ -33,7 +33,7 @@ Updated on Nov 6, 2023. - Support drop-in acceleration - [ComfyUI Nodes](https://github.com/Oneflow-Inc/onediff/tree/main/onediff_comfy_nodes) - [Acceleration with oneflow_compile](https://github.com/Oneflow-Inc/onediff/blob/a38c5ea475c07b4527981ec5723ccac083ed0a9c/examples/text_to_image_sdxl.py#L53) -- Support multi-resolution input +- Multi-resolution inputs - [Multi-resolution input](https://github.com/Oneflow-Inc/onediff/blob/a38c5ea475c07b4527981ec5723ccac083ed0a9c/examples/text_to_image_sdxl_save_load.py#L65) - Save/load the compiled result, deploy on different environments - [Save and Load](https://github.com/Oneflow-Inc/onediff/blob/main/examples/text_to_image_sdxl_save_load.py) From 7d4e96a365057cf4013df43185babdb852f6b50f Mon Sep 17 00:00:00 2001 From: Xiaoyu Xu Date: Thu, 7 Dec 2023 11:41:11 +0800 Subject: [PATCH 6/7] Update README.md --- README.md | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/README.md b/README.md index 9630da4ea..7367dccb3 100644 --- a/README.md +++ b/README.md @@ -33,8 +33,7 @@ Updated on Nov 6, 2023. - Support drop-in acceleration - [ComfyUI Nodes](https://github.com/Oneflow-Inc/onediff/tree/main/onediff_comfy_nodes) - [Acceleration with oneflow_compile](https://github.com/Oneflow-Inc/onediff/blob/a38c5ea475c07b4527981ec5723ccac083ed0a9c/examples/text_to_image_sdxl.py#L53) -- Multi-resolution inputs - - [Multi-resolution input](https://github.com/Oneflow-Inc/onediff/blob/a38c5ea475c07b4527981ec5723ccac083ed0a9c/examples/text_to_image_sdxl_save_load.py#L65) +- [Multi-resolution input](https://github.com/Oneflow-Inc/onediff/blob/a38c5ea475c07b4527981ec5723ccac083ed0a9c/examples/text_to_image_sdxl_save_load.py#L65) - Save/load the compiled result, deploy on different environments - [Save and Load](https://github.com/Oneflow-Inc/onediff/blob/main/examples/text_to_image_sdxl_save_load.py) - [Change device to do multi-process serving](https://github.com/Oneflow-Inc/onediff/blob/main/examples/text_to_image_sdxl_mp_load.py) From 858f84a63f8dd68ff865a6b5affc694ddd60e3f0 Mon Sep 17 00:00:00 2001 From: Xiaoyu Xu Date: Thu, 7 Dec 2023 11:41:33 +0800 Subject: [PATCH 7/7] Update README.md Co-authored-by: Shenghang Tsai --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 7367dccb3..787993024 100644 --- a/README.md +++ b/README.md @@ -30,7 +30,7 @@ Updated on Nov 6, 2023. - [ControlNet](https://github.com/Oneflow-Inc/onediff/blob/main/examples/text_to_image_controlnet.py) - [LCM](https://github.com/Oneflow-Inc/onediff/blob/main/examples/text_to_image_lcm.py) and [LCM LoRA](https://github.com/Oneflow-Inc/onediff/blob/main/examples/text_to_image_lcm_lora_sdxl.py) - [SDXL Turbo](https://github.com/Oneflow-Inc/onediff/blob/main/examples/text_to_image_sdxl_turbo.py) -- Support drop-in acceleration +- Drop-in acceleration - [ComfyUI Nodes](https://github.com/Oneflow-Inc/onediff/tree/main/onediff_comfy_nodes) - [Acceleration with oneflow_compile](https://github.com/Oneflow-Inc/onediff/blob/a38c5ea475c07b4527981ec5723ccac083ed0a9c/examples/text_to_image_sdxl.py#L53) - [Multi-resolution input](https://github.com/Oneflow-Inc/onediff/blob/a38c5ea475c07b4527981ec5723ccac083ed0a9c/examples/text_to_image_sdxl_save_load.py#L65)