| # Diffusers ControlNet Impl. & Reference Impl. generated image comparison | |
| ## Implementation Source Code & versions | |
| - Diffusers (in development version): https://github.com/takuma104/diffusers/tree/e758682c00a7d23e271fd8c9fb7a48912838045c | |
| - Reference Impl.: https://github.com/lllyasviel/ControlNet/tree/ed0439b37ce0872789e425d46381e892dbc9b407 | |
| ## Environment | |
| - OS: Ubuntu 22.04 | |
| - GPU: Nvidia RTX3090 | |
| - Cuda: 11.7 | |
| - Pytorch: 1.13.1 | |
| ## Scripts to generate plots: | |
| - Create control image: [create_control_images.py](create_control_images.py) | |
| - Diffusers generated image: [gen_diffusers_image.py](gen_diffusers_image.py) | |
| - Reference generated image: [gen_reference_image.py](gen_reference_image.py) | |
| - Create Plots: [create_plots.py](create_plots.py) | |
| ## Original image for control image: | |
| - All images from [test_imgs](https://github.com/lllyasviel/ControlNet/tree/main/test_imgs) excepts vermeer image. Croped and resized to 512x512px. | |
| <img width="128" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/control_images/bird_512x512.png" /> | |
| <img width="128" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/control_images/human_512x512.png" /> | |
| <img width="128" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/control_images/room_512x512.png" /> | |
| <img width="128" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/control_images/vermeer_512x512.png" /> | |
| ## Generate Settings: | |
| #### Control Images: | |
| Converted above original images by [controlnet_hinter](https://github.com/takuma104/controlnet_hinter). | |
| #### Prompts: | |
| All images were generated with the same prompt. | |
| - Prompt: `best quality, extremely detailed` | |
| - Negative Prompt: `lowres, bad anatomy, worst quality, low quality` | |
| #### Ohter setting (both common): | |
| - sampler: DDIM | |
| - guidance_scale: 9.0 | |
| - num_inference_steps: 20 | |
| - initial random latents: created on CPU using the seed | |
| ## Results: | |
| <img width="720" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/plots/figure_canny.png" /> | |
| <img width="720" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/plots/figure_depth.png" /> | |
| <img width="720" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/plots/figure_hed.png" /> | |
| <img width="720" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/plots/figure_mlsd.png" /> | |
| <img width="720" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/plots/figure_normal.png" /> | |
| <img width="720" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/plots/figure_openpose.png" /> | |
| <img width="720" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/plots/figure_scribble.png" /> | |
| <img width="720" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/plots/figure_seg.png" /> | |
| <!-- [](plots/figure_canny.png) | |
| [](plots/figure_depth.png) | |
| [](plots/figure_hed.png) | |
| [](plots/figure_mlsd.png) | |
| [](plots/figure_normal.png) | |
| [](plots/figure_openpose.png) | |
| [](plots/figure_scribble.png) | |
| [](plots/figure_seg.png) --> | |