Simple workflow with upscale, inpainting and outpainting.
Runtime profile
Source description
Simple workflow with upscale, inpainting and outpainting.
Inpainting mask supported only on image 1. When inpait switch is enabled, only masked area processed, leaving the rest of image original.
If you decide to use Abliterated version of clip model
Qwen2.5-VL-7B-Abliterated-Caption-it.Q8_0.gguf
you need to have
Qwen2.5-VL-7B-Abliterated-Caption-it.mmproj-F16.gguf
file in same folder
Works only with 2511 Qwen Image Edit model
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
Use the Qwen Image Edit 2511 workflow to process image inputs for upscaling, inpainting, and outpainting, producing processed images; for inpainting, it accepts a mask on image 1 and leaves the rest of the original image unchanged.
For inpainting, use an input image with a mask on image 1.
When the inpaint switch is enabled, only the masked area is processed and the rest of the original image remains unchanged.
Use it only with the 2511 Qwen Image Edit model.
If you use Qwen2.5-VL-7B-Abliterated-Caption-it.Q8_0.gguf, keep Qwen2.5-VL-7B-Abliterated-Caption-it.mmproj-F16.gguf in the same folder.
Listed node packs include ComfyUI_Comfyroll_CustomNodes, comfyui-crystools, comfyui-custom-scripts, comfyui-easy-use, comfyui-gguf, comfyui-kjnodes, comfyui-lora-manager, ComfyUI-nunchaku, RES4LYF, and rgthree-comfy.
The listed upscaler is seedvr2_videoupscaler.
Listed model files include ema_vae_fp16.safetensors, qwen_2.5_vl_7b_fp8_scaled.safetensors, qwen_image_edit_2511_fp8mixed.safetensors, qwen_image_vae.safetensors, Qwen-Image-Edit-2509-Q6_K.gguf, Qwen2.5-VL-7B-Abliterated-Caption-it.Q8_0.gguf, seedvr2_ema_7b_sharp-Q4_K_M.gguf, and
Enable the inpaint switch when you want edits limited to the masked area of image 1.
Suggestion · not verified
Before use, check that the files you need are present and match the listed names.
Suggestion · not verified
No license is specified for this workflow.
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
1 excerptSource context: 1278 downloads · Type Workflows · Base model Qwen
Estimated VRAM requirement
Estimate unavailable
15.7 GB across 1 of 9 model files. Model file total + 25% loading overhead + 2 GB execution buffer, rounded up.
Requirements
19 requirementsema_vae_fp16.safetensors
ConflictVAE · Unknown
qwen_2.5_vl_7b_fp8_scaled.safetensors
ConflictText encoder · Unknown
Possible sources
qwen_image_edit_2511_fp8mixed.safetensors
ConflictCheckpoint · Unknown
Possible sources
VAE · Unknown
Checkpoint · 15.7 GB · GGUF · fp8 · full · Unknown
Qwen2.5-VL-7B-Abliterated-Caption-it.Q8_0.gguf
Not resolvedText encoder · Unknown
seedvr2_ema_7b_sharp-Q4_K_M.gguf
Not resolvedCheckpoint · Unknown
seedvr2_videoupscaler
Not resolvedUpscaler · Registry
svdq-int4_r128-qwen-image-edit-2509.safetensors
Not resolvedCheckpoint · Unknown
Node pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
comfyui-gguf
PossibleNode pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry