Qwen Image Edit Rapid AIO GGUF
by Phil2Sat
Open source · 37k downloads · 202 likes
2.9
(202 reviews)ImageAPI & LocalAbout
The Qwen Image Edit Rapid AIO GGUF model is designed for AI-assisted image editing and generation. It enables the transformation of existing images or the creation of new ones from text descriptions, with an approach optimized for speed and efficiency. Its key capabilities include image editing (modifying details, adding or removing elements) and generation from prompts, while integrating advanced features such as specialized LoRA models. Ideal for digital artists, content creators, or developers looking to automate retouching or visual creation tasks, it stands out for its compatibility with tools like ComfyUI and its lightweight design thanks to the GGUF format. Its main strength lies in its versatility, combining generation and editing in a single model optimized for performance.
Documentation
Only quants of https://huggingface.co/Phr00t/Qwen-Image-Edit-Rapid-AIO
No AIO, just NSFW and Lightning loras included, packaging VAE and text_encoder into GGUF is not possible ATM, needs the text encoder and the VAE.
READ CAREFULLY!!!
I personally recommend: Qwen2.5-VL-7B-Instruct-abliterated but the default text_encoder does also fine. I have cloned the abliberated files into my repo and fixed the mmproj ready to use.
!!! PLACE THE mmproj FILE NEXT TO THE Qwen2.5-VL-7B-Instruct-abliterated.xxx.gguf !!! "mat1 and mat2 shapes cannot be multiplied..." is the error you get if you don't
VAE https://huggingface.co/calcuis/pig-vae/blob/main/pig_qwen_image_vae_fp32-f16.gguf
Replace comfy_extras/nodes_qwen.py with https://huggingface.co/Phr00t/Qwen-Image-Edit-Rapid-AIO/blob/main/fixed-textencode-node/nodes_qwen.py
workflow text2image 4-step Q2_K:
workflow edit of this image 4-step Q2_K:
workflow edit of this image 4-step Q5_K_M:
Capabilities & Tags
comfyUIggufqwenqwen-editt2ii2itext-to-imageendpoints_compatibleconversational
Links & Resources