Test Results and Guidelines on Using Qwen-Image-2.1 on Google Colab to Generate/Edit Images
Here are some results from using the Qwen Image 2.1 model via a google colab notebook for image generation and editing. The following image generations and edits were done on the T4 GPU offered by google Colab with the following specs: System RAM : 51.0 GB, VRAM : 16 GB Generating a 1K image Task: Text to Image Generation Prompt: A Young man in casual clothes and a busty and shapely young woman in a minidress are sitting on a branch of tree in the forest, smiling at each other Seed: 42 Qwen-Image Model Used: qwen-image-2.1-UC-Q4_K_M.gguf Output Image Size: 1344x768 Steps: 6 Sampler: euler Viggle turbo Lora Name: Qwen-Image-2.1-viggle-turbo-v0.2.1-6step-lora-r256.safetensors Completed in 2 min 40.62 sec Editing an Image with multiple instructions. Task: Image Editing Prompt: Change the woman's dress to a office wear and change the background to an office. Seed: 42 Qwen-Image Model Used: qwen-image-2.1-UC-Q4_K_M.gguf First reference image size: 576x1024 Output Image Size: 1152x2048 ...