# 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. ## 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: