Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Custom nodes for ComfyUI such as CLIP Text Encode++
| Date | Stars |
|---|---|
| 2026-07-30 | 326 |
| 2026-08-09 | 328 |
| 2026-08-17 | 329 |
| 2026-09-04 | 330 |
| 2026-09-22 | 330 |
| 2026-09-23 | 331 |
| 2026-10-04 | 333 |
| 2026-10-11 | 333 |
| 2026-10-12 | 333 |
| 2026-10-13 | 333 |
| 2026-10-14 | 333 |
| 2026-10-15 | 332 |
| 2026-10-16 | 333 |
| 2026-10-19 | 334 |
| 2026-10-22 | 334 |
| 2026-10-25 | 335 |
| 2026-10-29 | 336 |
| 2026-11-04 | 335 |
Today
-1 stars today
This week
— stars this week
This month
+2 stars this month
Momentum
0.0
growth rate 0.00%/day
# smZNodes
A selection of custom nodes for [ComfyUI](https://github.com/comfyanonymous/ComfyUI).
1. [CLIP Text Encode++](#clip-text-encode)
2. [Settings](#settings)
Contents
* [Tips to get reproducible results on both UIs](#tips-to-get-reproducible-results-on-both-uis)
* [FAQs](#faqs)
* [Installation](#installation)
## CLIP Text Encode++
<p align="center">
<div class="row">
<p align="center">
<img width="1255" alt="Clip Text Encode++ – Default settings on stable-diffusion-webui" src="https://github.com/shiimizu/ComfyUI_smZNodes/assets/54494639/ec85fd20-2b83-43cd-9f19-5aba34034e2a">
</div>
</p>
CLIP Text Encode++ can generate identical embeddings from [stable-diffusion-webui](https://github.com/AUTOMATIC1111/stable-diffusion-webui) for [ComfyUI](https://github.com/comfyanonymous/ComfyUI).
This means you can reproduce the same images generated from `stable-diffusion-webui` on `ComfyUI`.
Simple prompts generate _identical_ images. More complex prompts with complex attention/emphasis/weighting may generate images with slight differences. In that case, you can try using the `Settings` node to match outputs.
### Features
- [Prompt editing](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#prompt-editing)
- [Alternating words](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#alternating-words)
- [`AND`](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#composable-diffusion) keyword (similar to the ConditioningCombine node)
- [`BREAK`](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#break-keyword) keyword (same as the ConditioningConcat node)
- Weight normalization
- Optional `embedding:` identifier
### Comparisons
These images can be dragged into ComfyUI to load their workflows. Each image is done using the [Silicon29](https://huggingface.co/Xynon/SD-Silicon) (in SD v1.5) checkpoint with 18 steps using the Heun sampler.
|stable-diffusion-webui|A1111 parser|Comfy parser|
|:---:|:---:|:---:|
|  |  |  |
|  |  |  |
Image slider links:
- https://imgsli.com/MTkxMjE0
- https://imgsli.com/MTkxMjEy
### Options
|Name|Description|
| --- | --- |
| `parser` | The parser to parse prompts into tokens and then transformed (encoded) into embeddings. Taken from [SD.Next](https://github.com/vladmandic/automatic/discussions/99#discussioncomment-5931014). |
| `mean_normalization` | Whether to take the mean of your prompt weights. It's `true` by default on `stable-diffusion-webui`.<br>This is implemented according to how it is in `stable-diffusion-webui`. |
| `multi_conditioning` | <blockquote> For each prompt, the list is obtained by splitting the prompt using the `AND` separator. <br>See: [Compositional Visual Generation with Composable Diffusion Models](https://energy-based-model.github.io/Compositional-Visual-Generation-with-Composable-Diffusion-Models/) </blockquote> <ul><li>a way to use multiple prompts at once</li><li>supports weights for prompts: `a cat :1.2 AND a dog AND a penguin :2.2` (for non-comfy parsers). The weights default to 1</li><li>each prompExcerpt of 9,239 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:209534b08f6fec6f, topic:stable-diffusion, topic:comfyui, readme:stable diffusion