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

Steps: 6
 
Sampler: euler

Viggle turbo Lora Name: Qwen-Image-2.1-viggle-turbo-v0.2.1-6step-lora-r256.safetensors

Completed in 10 min 13.95 sec


Removing the background of an image


Task: Image Editing

Prompt: This is an RGBA image with transparency. A beautiful woman in a black gown. The image has alpha channel and the background is transparent.

Seed: 42

Qwen-Image Model Used: qwen-image-2.1-UC-Q4_K_M.gguf

First reference image size: 576x1024

Number of Input Images: 1

Output Image Size: 576x1024

Steps: 6

Sampler: euler

Viggle turbo Lora Name: Qwen-Image-2.1-viggle-turbo-v0.2.1-6step-lora-r256.safetensors

Completed in 1 min 58.50 sec


Using multiple references





Task: Image Editing

Prompt: These three characters are sitting around a campfire in a forest
 
Seed: 42

Qwen-Image Model Used: qwen-image-2.1-UC-Q4_K_M.gguf

First reference image size: 576x1024

Number of Input Images: 3

Output Image Size: 1024x1792

Steps: 6

Sampler: euler

Viggle turbo Lora Name: Qwen-Image-2.1-viggle-turbo-v0.2.1-6step-lora-r256.safetensors

Completed in 13 min 21.80 sec



Generating 2K Images

The following 2K images were generated with the L4 GPU in google colab with the following specs :

System RAM : 53.0 GB, VRAM : 22.5 GB



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_bf16.safetensors (Comfy-Org)

Text Encoder: qwen3vl_8b_int8_convrot.safetensors

Output Image Size: 2752x1536

Steps: 40

CFG: 1

Sampler: euler

Scheduler: simple

Completed in 5 min 13.47 sec (Probably lengthened by my unstable network)


Here's the same generation using the viggle turbo LoRA for a 2K 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_bf16.safetensors (Comfy-Org)

Text Encoder: qwen3vl_8b_int8_convrot.safetensors

Output Image Size: 2752x1536

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 17.64 sec


Here's another generation without a LoRA but with 25 steps.


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_bf16.safetensors (Comfy-Org)

Output Image Size: 2752x1536

Steps: 25

CFG: 1

Sampler: euler

Scheduler: simple

Cache Enabled: True

Cache dtype: int8

Completed in 3 min 23.22 sec


Using the Notebook

To be continued...








Comments

Post a Comment

Popular posts from this blog

How to use Wan2.2 Google Colab Notebooks for Image to Video Generation

Image
You can also watch  this video guide. This is a guide on how to use two recently released wan2.2 google colab notebooks for a highly impressive image to video generation that compares favorably with similar platforms like Seedance 1.0, Hailuo 02, and Kling 2.0. Wan 2.2, which is an improvement on wan2.1, is the top open-source video generation model at the time of writing this guide, and the LoRAs built on wan2.1 can still work with wan2.2. This significantly expands its video generation capabilities. You can learn more about wan2.2 from this github repository:   https://github.com/Wan-Video/Wan2.2   Notebook 1 (Free!) The first notebook is titled WAN2.2 IMAGE TO VIDEO WITH LIGHTX2V LoRA and it can be found in this github repository: https://github.com/Isi-dev/Google-Colab_Notebooks . This notebook enables you to generate at least 5 seconds of a standard definition video from a single image for free in about 13 minutes using the T4 GPU offered by google colab....
Read more

Generating Long, High-Quality AI Videos with LongCat-Video in ComfyUI (Google Colab Setup)

Image
  A 27-minute 15fps video generated with ComfyUI on Google Colab.  LongCat-Video is an AI project that pushes the limits of video generation.  Unlike most AI video models that degrade in color or consistency after a few seconds, LongCat-Video enables generating videos longer than 30 seconds,  all while maintaining sharp image quality and stable colors . The models and code were optimized for ComfyUI by Kijai , one of the major contributors to the ComfyUI ecosystem. This optimization makes it much easier to experiment with LongCat-Video and generate long, coherent video sequences right from your browser. Running LongCat-Video on Google Colab I’ve created a Google Colab notebook that automatically sets up ComfyUI with the LongCat-Video models. So far, I’ve tested it on the L4 GPU , but it should also work on the free  T4 if you reduce the number of frames generated per sequence and set blocks_to_swap to 0 if the RAM crashes with the default settings. ...
Read more

I dumped Kling AI for these colab notebooks

Image
This guide shows you how to use two Google Colab notebooks for turning a single image into a 5 second video with free and one time payment options. With models like WAN 2.1 and LoRAs like causvid, lightx2v, and fusionx, you can generate realistic or stylized videos in under 10 minutes using the free T4 GPU. You’ll also learn how to enhance videos, upscale them to 720p, fix faces, and interpolate frames.  Compared to subscription services like Kling AI, this setup gives you full control, no watermark, and excellent results. Notebook 1 (Free!) Click this link to access this notebook The first notebook is titled Faster WAN 2.1 IMAGE TO VIDEO WITH CAUSVID, LIGHTX2V, & FUSION-X LoRAs and it is a significant improvement over the widely loved WAN IMAGE TO VIDEO WITH Q4 & Q6 GGUF MODELS, LORA, & TEACACHE notebook which can be found in this github repository: https://github.com/Isi-dev/Google-Colab_Notebooks . This notebook enables you to generate at least 5 second 16fps sta...
Read more