nathannlu/aperture
🔬 Visualize attention layers from Stable Diffusion
This tool helps researchers and artists understand how Stable Diffusion models interpret text prompts to create images. You input a text prompt and an image generated by the model, and it outputs visual overlays showing which parts of the image correspond to each word in your prompt. This is useful for anyone working with generative AI models like Stable Diffusion to analyze and refine their creative outputs.
No commits in the last 6 months.
Use this if you need to visualize how a Stable Diffusion model's attention layers process a text prompt to generate specific features in an image.
Not ideal if you are looking for a tool to generate images directly or to visualize other types of AI models besides Stable Diffusion.
Stars
92
Forks
4
Language
TypeScript
License
—
Category
Last pushed
Apr 01, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/nathannlu/aperture"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
scraed/LanPaint
High quality training free inpaint for every stable diffusion model. Supports ComfyUI
julienkay/com.doji.diffusers
A Unity package to run pretrained diffusion models with Unity Sentis
apapiu/transformer_latent_diffusion
Text to Image Latent Diffusion using a Transformer core
Aatricks/LightDiffusion-Next
Fastest Diffusion backend, WebUI, server. Pushing implementation and discovery of optimizations...
FMXExpress/Stable-Diffusion-Desktop-Client
Stable Diffusion Desktop client for Windows, macOS, and Linux built in Embarcadero Delphi.