Hello!
Version 2511 v1:
This workflow works fine with 8GB VRAM, if you have a better card, you might want to disable the Lightning LoRA, add more steps, and cfg to every KSampler. Maybe 20 steps and cfg 2.5? You should try. Unlike the previous versions of this workflow, this has a custom node and uses a Q version.
Resources:
[Model] Qwen-image-edit-2511-Q2_K.gguf:
[CLIP] qwen_2.5_vl_7b_fp8_scaled
[VAE] qwen_image_vae
[Nodes] Comfyui-QwenEditUtils
About the prompts:
These prompts are just examples, so you might want to change them, because, depending on the original image they may work or may not work. Also, I totally recommend translating the prompts to Simplified Chinese, because in that language they will have more adherence. For example: First prompt is orbit the camera 45 degrees. Second prompt is right-side. Third prompt is zoom out. You can use English too, but, you'll need better luck.
_____________________________
Previous version text:
Hello!
People asked me to update this workflow, so, here it is! This version uses:
And 8 steps LoRA:
Also, I added a secondary image, if you want to add something to your new images, if you don't want, you can disable the load node. Remember always to change the prompts to do what you need.
The file you'll download has the JSON file as well as a PNG, so you can use either in ComfyUI
Cya!
_____________________________
Previous version (1.0):
Hello!
I'm kinda new to ComfyUI, so I made this spaghetti nightmare, this will create 6 different images from one image using Qwen Image Edit with 4 steps each one (I'm low VRAM!).
Files used:
Model: qwen_image_edit_fp8_e4m3fn
Lora: Qwen-Image-Lightning-4steps-V1.0
Clip: qwen_2.5_vl_7b_fp8_scaled
Vae: qwen_image_vae
Have fun!
Description
Model: Qwen Image Edit 2509 (Plus)
LoRA: Lightning 8 steps V2
FAQ
Comments (14)
i keep getting a black output image. not sure what im doing wrong.
Did you update the ComfyUI to the latest version?
disable sage attention
@Burning_Dark Thank you so much, it was the Sage Attention. i was using the run_nvidia_gpu_SageAttention.bat
@gabrielxThanks for the reply. It was the Sage attention. ComfyUI was already updated.
You can still use Sage Attention by applying the Sage Attention KJ patch node if you want, using the sageattn_qk_int8_pv_fp16_cuda value.
Thank you for this great workflow. Here is a question for you: with the LORA (lightning 8 step v2) on, the workflows works excellent and I get an alternate "perspective" or whatever else I write in prompts. However, when I turn the LORA off, the image output is horrific, it doesn't follow the original image well and the quality varies (I turned it off to up the quality while also upping the steps). Any idea why this might happen?
May be its time to add info that your workflow requires 5090? Most of users not have it.
Why make people waste time until they see which huge checkpoint need for your workflow.
It doesn't requires that, unless my RTX 3070 with 8 GB VRAM magically got some steroids.
What your problem？
这只是一个很简单的工作流，不至于绑定5090
Corriendo en una 3060 de 12 gb
tiempo de generacion
Prompt executed in 560.13 seconds