Skip to content

Qwen Edit - Multiple Camera Angles

Video Lecture

Section Video Links
Qwen Edit - Multiple Camera Angles Qwen Edit - Multiple Camera Angles Qwen Edit - Multiple Camera Angles

Description

Qwen (short for Tongyi Qianwen)

Qwen Edit is another great imaging editing model.

We will experiment with changing camera positions and angles.

Download all of these and place into correct folders.

Download only one of these depending on how much VRAM you have.

📂 ComfyUI/
├── 📂 models/
│   ├── 📂 diffusion_models/
│   │      └── qwen_image_edit_2509_fp8_e4m3fn.safetensors
│   ├── 📂 loras/
│   │      ├── Qwen-Edit-2509-Multiple-angles.safetensors
│   │      └── Qwen-Image-Edit-2509-Lightning-4steps-V1.0-bf16.safetensors
│   ├── 📂 text_encoders/
│   │      └── qwen_2.5_vl_7b_fp8_scaled.safetensors
│   ├── 📂 unet/
│   │      ├── Qwen-Image-Edit-2509-Q8_0.gguf
│   │      └── Qwen-Image-Edit-2509-Q3_K_M.gguf
│   └── 📂 vae/
│          └── qwen_image_vae.safetensors

Start Workflow

Initial Image Workflow
qwen edit initial 1 qwen edit workflow
qwen edit initial 2

  • ModelSamplingAuraFlow : An advanced tool for fine-tuning image generation by applying a "shift" parameter to the model, allowing users to control the balance between overall composition (higher shift for more freedom) and fine details (lower shift for control).

  • CFGNorm (CFG Normalization): CFGNorm is used to prevent image over saturation that can occur when using high CFG values, which can be useful when a prompt isn't showing up well at low CFG settings.

WGET Commands

If you are using Runpod, or a similar hosted GPU service, then you can access your running pod/instance using a terminal.

#
#
#
# CD into ./ComfyUI/models/loras folder
wget https://huggingface.co/Comfy-Org/Qwen-Image-Edit_ComfyUI/resolve/main/split_files/loras/Qwen-Edit-2509-Multiple-angles.safetensors
wget https://huggingface.co/lightx2v/Qwen-Image-Lightning/resolve/main/Qwen-Image-Edit-2509/Qwen-Image-Edit-2509-Lightning-4steps-V1.0-bf16.safetensors

#
#
# CD into ./ComfyUI/models/text_encoders/ folder
wget https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/text_encoders/qwen_2.5_vl_7b_fp8_scaled.safetensors

#
#
# CD into ./ComfyUI/models/vae/ folder
wget https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/vae/qwen_image_vae.safetensors

Download only one of these next 3 models.

#
#
# CD into ./ComfyUI/models/diffusion_models/ folder
wget https://huggingface.co/Comfy-Org/Qwen-Image-Edit_ComfyUI/resolve/main/split_files/diffusion_models/qwen_image_edit_2509_fp8_e4m3fn.safetensors

#
#
#
# CD into ./ComfyUI/models/unet/ folder
wget https://huggingface.co/QuantStack/Qwen-Image-Edit-2509-GGUF/resolve/main/Qwen-Image-Edit-2509-Q8_0.gguf
wget https://huggingface.co/QuantStack/Qwen-Image-Edit-2509-GGUF/resolve/main/Qwen-Image-Edit-2509-Q3_K_M.gguf

Wait for files to download fully before running your workflows.