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

[WIP][Community Pipeline] InstaFlow! One-Step Stable Diffusion with Rectified Flow #6057

Merged
merged 18 commits into from
Jan 23, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
39 changes: 39 additions & 0 deletions examples/community/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -55,6 +55,7 @@ prompt-to-prompt | change parts of a prompt and retain image structure (see [pap
| LDM3D-sr (LDM3D upscaler) | Upscale low resolution RGB and depth inputs to high resolution | [StableDiffusionUpscaleLDM3D Pipeline](https://github.com/estelleafl/diffusers/tree/ldm3d_upscaler_community/examples/community#stablediffusionupscaleldm3d-pipeline) | - | [Estelle Aflalo](https://github.com/estelleafl) |
| AnimateDiff ControlNet Pipeline | Combines AnimateDiff with precise motion control using ControlNets | [AnimateDiff ControlNet Pipeline](#animatediff-controlnet-pipeline) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1SKboYeGjEQmQPWoFC0aLYpBlYdHXkvAu?usp=sharing) | [Aryan V S](https://github.com/a-r-r-o-w) and [Edoardo Botta](https://github.com/EdoardoBotta) |
| DemoFusion Pipeline | Implementation of [DemoFusion: Democratising High-Resolution Image Generation With No $$$](https://arxiv.org/abs/2311.16973) | [DemoFusion Pipeline](#DemoFusion) | - | [Ruoyi Du](https://github.com/RuoyiDu) |
| Instaflow Pipeline | Implementation of [InstaFlow! One-Step Stable Diffusion with Rectified Flow](https://arxiv.org/abs/2309.06380) | [Instaflow Pipeline](#instaflow-pipeline) | - | [Ayush Mangal](https://github.com/ayushtues) |
| Null-Text Inversion Pipeline | Implement [Null-text Inversion for Editing Real Images using Guided Diffusion Models](https://arxiv.org/abs/2211.09794) as a pipeline. | [Null-Text Inversion](https://github.com/google/prompt-to-prompt/) | - | [Junsheng Luan](https://github.com/Junsheng121) |
| Rerender A Video Pipeline | Implementation of [[SIGGRAPH Asia 2023] Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation](https://arxiv.org/abs/2306.07954) | [Rerender A Video Pipeline](#Rerender_A_Video) | - | [Yifan Zhou](https://github.com/SingleZombie) |
| StyleAligned Pipeline | Implementation of [Style Aligned Image Generation via Shared Attention](https://arxiv.org/abs/2312.02133) | [StyleAligned Pipeline](#stylealigned-pipeline) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://drive.google.com/file/d/15X2E0jFPTajUIjS0FzX50OaHsCbP2lQ0/view?usp=sharing) | [Aryan V S](https://github.com/a-r-r-o-w) |
Expand Down Expand Up @@ -3228,6 +3229,43 @@ output_image.save("./output.png")

```

### Instaflow Pipeline
InstaFlow is an ultra-fast, one-step image generator that achieves image quality close to Stable Diffusion, significantly reducing the demand of computational resources. This efficiency is made possible through a recent [Rectified Flow](https://github.com/gnobitab/RectifiedFlow) technique, which trains probability flows with straight trajectories, hence inherently requiring only a single step for fast inference.

```python
from diffusers import DiffusionPipeline
import torch


pipe = DiffusionPipeline.from_pretrained("XCLIU/instaflow_0_9B_from_sd_1_5", torch_dtype=torch.float16, custom_pipeline="instaflow_one_step")
pipe.to("cuda") ### if GPU is not available, comment this line
prompt = "A hyper-realistic photo of a cute cat."

images = pipe(prompt=prompt,
num_inference_steps=1,
guidance_scale=0.0).images
images[0].save("./image.png")
```
![image1](https://huggingface.co/datasets/ayushtues/instaflow_images/resolve/main/instaflow_cat.png)

You can also combine it with LORA out of the box, like https://huggingface.co/artificialguybr/logo-redmond-1-5v-logo-lora-for-liberteredmond-sd-1-5, to unlock cool use cases in single step!

```python
from diffusers import DiffusionPipeline
import torch


pipe = DiffusionPipeline.from_pretrained("XCLIU/instaflow_0_9B_from_sd_1_5", torch_dtype=torch.float16, custom_pipeline="instaflow_one_step")
pipe.to("cuda") ### if GPU is not available, comment this line
pipe.load_lora_weights("artificialguybr/logo-redmond-1-5v-logo-lora-for-liberteredmond-sd-1-5")
prompt = "logo, A logo for a fitness app, dynamic running figure, energetic colors (red, orange) ),LogoRedAF ,"
images = pipe(prompt=prompt,
num_inference_steps=1,
guidance_scale=0.0).images
images[0].save("./image.png")
```
![image0](https://huggingface.co/datasets/ayushtues/instaflow_images/resolve/main/instaflow_logo.png)

### Null-Text Inversion pipeline

This pipeline provides null-text inversion for editing real images. It enables null-text optimization, and DDIM reconstruction via w, w/o null-text optimization. No prompt-to-prompt code is implemented as there is a Prompt2PromptPipeline.
Expand Down Expand Up @@ -3267,6 +3305,7 @@ pipeline(prompt, uncond, inverted_latent, guidance_scale=7.5, num_inference_step
```
### Rerender_A_Video

```
This is the Diffusers implementation of zero-shot video-to-video translation pipeline [Rerender_A_Video](https://github.com/williamyang1991/Rerender_A_Video) (without Ebsynth postprocessing). To run the code, please install gmflow. Then modify the path in `examples/community/rerender_a_video.py`:

```py
Expand Down
Loading
Loading