Glitch-Img-1.0: RGBA Image Generation & Editing with Qwen-Image-2.1

Try it: huggingface.co/ISLAM-PO/Glitch-Img-1.0 · image-gen demo Space

Image generation has moved past "pretty pictures" toward controllable, editable, transparent assets. Glitch-Img-1.0 is my re-upload of Qwen/Qwen-Image-2.1 under the name ISLAM-PO/Glitch-Img-1.0, aimed at making a strong unified text-to-image + editing model easy to discover and use from a single, well-documented repository. All weights and configs are unchanged from the original; only the README and repo IDs were updated, and the model is Built with Qwen under the Qwen Research License (non-commercial).

This report covers what the model does, its key capabilities, a quick-start, memory tips, and licensing notes.

Four headline improvements define the Qwen-Image-2.1 family this build inherits:

pip install torch> = 2.4.0 pip install transformers> = 5.17 pip install git+https://github.com/huggingface/diffusers pip install accelerate pillow Enter fullscreen mode Exit fullscreen mode Text-to-image:

import torch from diffusers import QwenImage21Pipeline pipe = QwenImage21Pipeline. from_pretrained ( " ISLAM-PO/Glitch-Img-1.0 ", torch_dtype = torch. bfloat16 ). to ( " cuda " ) image = pipe ( prompt = ' A neon shop sign that reads " GLITCH IMG 1.0 ", rainy night, reflections on wet pavement ', width = 2048, height = 2048, num_inference_steps = 40, generator = torch. Generator ( " cuda " ). manual_seed ( 42 ), ). images [ 0 ] image. save ( " t2i_example.png " ) Enter fullscreen mode Exit fullscreen mode Image editing:

import torch from PIL import Image from diffusers import QwenImage21Pipeline pipe = QwenImage21Pipeline. from_pretrained ( " ISLAM-PO/Glitch-Img-1.0 ", torch_dtype = torch. bfloat16 ). to ( " cuda " ) input_image = Image. open ( " input.png " ) image = pipe ( prompt = " Change the background to a sunset beach ", image = input_image, num_inference_steps = 40, generator = torch. Generator ( " cuda " ). manual_seed ( 42 ), ). images [ 0 ] image. save ( " edit_example.png " ) Enter fullscreen mode Exit fullscreen mode Transparent (RGBA) generation — use the recommended prompt format:

image = pipe ( prompt = " This is an RGBA image with transparency. A cute cartoon dragon sticker. " " The image has alpha channel and the background is transparent. ", width = 2048, height = 2048, num_inference_steps = 40, generator = torch. Generator ( " cuda " ). manual_seed ( 42 ), ). images [ 0 ] image. save ( " transparent_example.png " ) Enter fullscreen mode Exit fullscreen mode Aspect ratios:

aspect_ratios = { " 1:1 ": ( 2048, 2048 ), " 4:3 ": ( 2400, 1792 ), " 3:4 ": ( 1792, 2400 ), " 3:2 ": ( 2528, 1696 ), " 2:3 ": ( 1696, 2528 ), " 16:9 ": ( 2752, 1536 ), " 9:16 ": ( 1536, 2752 ), } Enter fullscreen mode Exit fullscreen mode 4. Memory Optimization pipe = QwenImage21Pipeline. from_pretrained ( " ISLAM-PO/Glitch-Img-1.0 ", torch_dtype = torch. bfloat16 ) pipe. enable_model_cpu_offload () Enter fullscreen mode Exit fullscreen mode This offloads model parts to CPU between steps, letting you run on smaller GPUs at the cost of speed.

I use Glitch-Img as the visual layer behind my portfolio and product work:

It complements MasryGPT (text) as the two halves of an Arabic-first AI product stack: one generates the words, the other the visuals.

Author: Islam Al-Nashar — Full-Stack Developer & AI builder. GitHub · Hugging Face · Portfolio