zer0int/ComfyUI-Nuke-a-Text-Encoder
For SDXL, SD1.5, Flux. Nuke T5 and let CLIP guide Flux.1 on its own! Or let let random guide Flux.1! Or load a CLIP crazy opinion embedding about your image and let that guide the AI!
This tool helps AI artists and researchers creatively manipulate how image generation models like SDXL or Flux.1 interpret text prompts. You can choose to 'nuke' or disable certain text encoder inputs, allowing other parts of the model (like CLIP or even random noise) to solely guide the image creation. It takes your text prompt and desired image generation model configuration and outputs unique, often unexpected, visual interpretations.
No commits in the last 6 months.
Use this if you want to experiment with advanced image generation techniques, explore model biases, or generate highly artistic and abstract images by influencing how AI models perceive your text prompts.
Not ideal if you need predictable and precise image generation directly aligned with your textual descriptions without abstract interpretations.
Stars
25
Forks
2
Language
Python
License
—
Category
Last pushed
Aug 05, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/zer0int/ComfyUI-Nuke-a-Text-Encoder"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
unum-cloud/UForm
Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts,...
rom1504/clip-retrieval
Easily compute clip embeddings and build a clip retrieval system with them
mazzzystar/Queryable
Run OpenAI's CLIP and Apple's MobileCLIP model on iOS to search photos.
s-emanuilov/litepali
LitePali is a minimal, efficient implementation of ColPali for image retrieval and indexing,...
slavabarkov/tidy
Offline semantic Text-to-Image and Image-to-Image search on Android powered by quantized...