ComfyUI_ADV_CLIP_emb
ComfyUI_Noise
ComfyUI_ADV_CLIP_emb | ComfyUI_Noise | |
---|---|---|
3 | 3 | |
244 | 195 | |
- | - | |
3.8 | 4.7 | |
about 1 month ago | 28 days ago | |
Python | Python | |
GNU General Public License v3.0 only | GNU General Public License v3.0 only |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
ComfyUI_ADV_CLIP_emb
-
Organized ComfyUI txt2Img-upscale workflow
Advanced CLIP Text Encode
-
Prompt weighting in SDXL 0.9
With SDXL on the horizon, I've gone ahead and updated my prompt weighting nodes for ComfyUI and did some quick testing.
-
Exploring different ways of interpreting token weighting using ComfyUI
There are different ways of interpreting the up or down-weighting of words in prompts. A1111 for instance simply scales the associated vector by the prompt weight, while ComfyUI by default calculates a travel direction from the prompt and an empty prompt. This results in markedly different behavior at higher weighting. I made a node for ComfyUI that lets you pick and mix different ways of interpreting these token weights, so that people can play around with and explore these things 😁. You can find the github page with a more in depth explanation here
ComfyUI_Noise
-
Organized ComfyUI txt2Img-upscale workflow
ComfyUI Noise
-
COMFYUI SDXL WORKFLOW INBOUND! Q&A NOW OPEN! (WIP EARLY ACCESS WORKFLOW INCLUDED!)
ComfyUI Noise can do it. Maybe that WAS has some nodes that let you do it? but haven't checked
-
Q&A with Katherine Forrest, a former federal judge for the SDNY, on copyright and generative AI, the Copyright Office's guidance on AI-generated work, and more (Nabiha Syed/The Markup)
The idea is pretty straight forwards, you just walk backwards in the noise schedule rather than forwards. If everything goes correctly you end up with something that should look like gaussian noise and reverts back to something resembling the original image within some margin e. A1111 has it listed as a feature here where they implement it for the euler solver. But in principle you can do this for any solver as long as the solver is deterministic see for instance here. This isn't doing clever stuff like analyzing it with CLIP to see exactly what it contains or anything, just running the process in reverse to get the mapping to the noise.
What are some alternatives?
deforum-for-automatic1111-webui - Deforum extension script for AUTOMATIC1111's Stable Diffusion webui [Moved to: https://github.com/deforum-art/sd-webui-deforum]
stable-dreamfusion - Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.
comfyui_segment_anything - Based on GroundingDino and SAM, use semantic strings to segment any element in an image. The comfyui version of sd-webui-segment-anything.
efficiency-nodes-comfyui - A collection of ComfyUI custom nodes. ⚠️ WARNING: This repo is no longer maintained.
ComfyUI-Workflow-Component - This is a side project to experiment with using workflows as components.
ComfyUI-Manager
ComfyUI_fabric - ComfyUI nodes based on the paper "FABRIC: Personalizing Diffusion Models with Iterative Feedback" (Feedback via Attention-Based Reference Image Conditioning)
IOPaint - Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.
images-grid-comfy-plugin - A simple comfyUI plugin for images grid (X/Y Plot)