Pony

🚀 gguf Quantized Legacy Models for Anime (Additional Test Pack for gguf-node)

This project provides gguf quantized legacy models for anime, serving as an additional test pack for gguf - node. It enables text - to - image generation with specific setup and workflow steps.

🚀 Quick Start

Setup (in general)

• Drag gguf file(s) to the diffusion models folder (./ComfyUI/models/diffusion_models).
• Drag clip or encoder(s), such as g - clip and l - clip, to the text encoders folder (./ComfyUI/models/text_encoders).
• Drag vae decoder(s), such as legacy - vae, to the vae folder (./ComfyUI/models/vae).

Run it straight (no installation needed way)

• Get the comfy pack with the new gguf - node here.
• Run the .bat file in the main directory.

Workflow

• Drag any workflow json file to the activated browser; or
• Drag any generated output file (e.g., picture, video, etc., which contains the workflow metadata) to the activated browser.
• Example workflow json for the [safetensors](https://huggingface.co/calcuis/pony/blob/main/workflow - safetensors - pony.json).
• Example workflow json for the [gguf](https://huggingface.co/calcuis/pony/blob/main/workflow - gguf - pony.json).

✨ Features

• Accuracy with Tags: Use tag/word(s) as input for more accurate results for those legacy models.
• Compatibility: Good to run on old machines, like 9xx series or before. It supports legacy mode (--disable - cuda - malloc --lowvram) and is compatible with the new gguf - node.
• Credit to Contributors: Credits should be given to those contributors from the civitai platform.

📄 License

This project is licensed under the Apache - 2.0 license.

📚 Documentation

Review

• For those legacy models, using tag/word(s) as input can yield more accurate results. However, it's not very convenient at the beginning compared to recent models.
• Some models (original files) are provided by someone else. It might be difficult to identify the creator/contributor(s) unless specified in the source. If it's your work, please let us know, and we'll address it properly.

Reference

• ComfyUI: comfyanonymous
• gguf - node: ([pypi](https://pypi.org/project/gguf - node)|repo|pack)

Widget Examples

Example 1

• Input Text: score_9, score_8_up, score_7_up, film grain, photo by fuji - proplus - ii film, raw picture of 20 years old woman in lingerie, portrait, deep blue sky, cloudy sky, outdoor, high key light, soft shadow, Fiery clouds, colored hair
• Parameters - Negative Prompt: score_6, score_5, score_4, source_pony, (worst quality:1.2), (low quality:1.2), (normal quality:1.2), lowres, bad anatomy, bad hands, signature, watermarks, ugly, imperfect eyes, skewed eyes, unnatural face, unnatural body, error, extra limb, missing limbs, painting by bad - artist
• Output: samples\ComfyUI_00001_.png

Example 2

• Input Text: drag it to browser <metadata> same descriptor to the 1st one; but different model (boleromix)
• Output: samples\ComfyUI_00002_.png

Example 3

• Input Text: drag it to browser <metadata> same descriptor to the 1st one; but different model (snow)
• Output: samples\ComfyUI_00003_.png