From b13df7c45433dea6da09ee1ced15bc5f4ba5c1bd Mon Sep 17 00:00:00 2001 From: MaximClouser Date: Wed, 26 Feb 2025 19:29:40 +0000 Subject: [PATCH] future work, hardware reqs --- README.md | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 49d4323..1b43de4 100644 --- a/README.md +++ b/README.md @@ -1,6 +1,6 @@ # ComfyUI-InferenceTimeScaling -A ComfyUI extension implementing "Inference-time scaling for diffusion models beyond scaling denoising steps" ([Ma et al., 2025](https://arxiv.org/abs/2501.09732)). This extension provides advanced inference-time optimization techniques to improve image generation quality through random search and zero-order optimization algorithms, along with an ensemble verification system. +A ComfyUI extension implementing "Inference-time scaling for diffusion models beyond scaling denoising steps" ([Ma et al., 2025](https://arxiv.org/abs/2501.09732)). This extension provides inference-time optimization techniques to enhance diffusion-based image generation quality through random search and zero-order optimization algorithms, along with an ensemble verification system. ## Features @@ -20,6 +20,12 @@ A ComfyUI extension implementing "Inference-time scaling for diffusion models be 1. Install [ComfyUI](https://github.com/comfyanonymous/ComfyUI) 2. Install [ComfyUI-Manager](https://github.com/ltdrdata/ComfyUI-Manager) +### Hardware Requirements + +This was developed and tested on a system with: +- Single NVIDIA L40S GPU (48GB VRAM) +- 62GB System RAM + ### Installation Methods #### Using ComfyUI-Manager (Recommended) @@ -117,6 +123,16 @@ Loads the ImageReward model for image quality assessment. 4. Set your desired search algorithm and parameters 5. Generate optimized images with improved quality +## Current Limitations + +- Single latent processing only (batch size = 1) - performance limitation +- Sequential verification (one image-text pair at a time) - speed bottleneck + +## Future Work + +- [ ] Add batch processing support for image generation (performance optimization) +- [ ] Implement batched verification for multiple image-text pairs (speed optimization) + ## Development To install development dependencies: