WorkflowAufgelistetExtern

Qwen Image Edit 2511 Ultimate — v1.0

Qwen Image Edit 2511 — 2-Image Edit Workflow (Base + Reference)

AufgabeMehrfachFähigkeitenBildbearbeitung · Bild zu Bild · HochskalierungFamilieQwen-ImageVersionRelease 2590009 — Qwen Image Edit 2511 Ultimate CIVITAI.jsonGeschätzte VRAMNot yet characterizedUnratedBewertung

Laufzeitprofil

Zugriff: Externer Arbeitsablauf
Status: Aufgelistet
Version: Qwen Image Edit 2511 Ultimate CIVITAI.json
Quelle: Civitai
Aktualisiert: 3. Nov. 2026

Quellenbeschreibung

No release description captured.

What you need

Model files: 29.9 GiB known subtotal

Remaining hardware or download-size estimates are not available yet.

Anforderungen

Modelle

CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors
Nicht aufgelöst
Clip Vision · Unknown
qwen_2.5_vl_7b_fp8_scaled.safetensors
Datei angegeben
Text encoder · 8.74 GB · Hugging Face · Comfy-Org/HunyuanVideo_1.5_repackaged
qwen_image_vae.safetensors
Repository zugeordnet
VAE · Hugging Face · Comfy-Org/Qwen-Image_ComfyUI
Qwen-Image-Edit-2511-Lightning-4steps-V1.0-bf16.safetensors
Gefunden
LoRA · 810 MB · SAFETENSOR · BF16 (tensor header) · Hugging Face · lightx2v/Qwen-Image-Edit-2511-Lightning
Qwen-Image-Edit-2511-Q8_0.gguf
Gefunden
Diffusion model · 20.3 GB · GGUF · Unknown
RealESRGAN_x4plus.pth
Gefunden
Upscaler · 63.9 MB · PTH · Unknown

Knotenpakete

comfyui-gguf
Möglich
Knotenpaket · Registry
comfyui-rmbg
GefundenOptional
Knotenpaket · Registry
Gefunden
Knotenpaket · Registry

KI-generierter Kommentar

KI-generierte Erklärung auf Grundlage von Quellen- und Konfigurationsdetails. Vorschläge sind klar gekennzeichnet.

Zweck

Use this workflow to edit a required Base Image with a required Reference Image and prompt, applying reference-guided style, clothing, background, detail, or product/mockup changes to produce an edited image that keeps the base composition.

Fluss

The Base Image anchors structure and layout; the Reference Image guides style and details, while your prompt says what to preserve or change.
The workflow includes image preview and saving stages, plus an image-upscaling stage.

Eingaben und Ausgaben

Provide two required images: a Base Image to edit and a Reference Image showing the target style, clothing, pose, composition, material, or other desired look; use your prompt to describe the changes.

Einrichtung

Choose a clean, high-resolution Reference Image with clear details relevant to the edit.
Vorschlag · nicht geprüft

Abhängigkeiten

Model files listed for the workflow are CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors, qwen_2.5_vl_7b_fp8_scaled.safetensors, qwen_image_vae.safetensors, Qwen-Image-Edit-2511-Lightning-4steps-V1.0-bf16.safetensors, Qwen-Image-Edit-2511-Q8_0.gguf, and RealESRGAN_x4plus.pth.
Listed ComfyUI node packs are comfyui-gguf (1.1.5), comfyui-rmbg (2.9.6, optional), and rgthree-comfy (1.0.2512071717).

Konfiguration

As starting values, try 4 steps, CFG 1, and Denoise/Strength 1.
Vorschlag · nicht geprüft
In your prompt, say what to preserve from the Base Image and what to apply from the Reference Image; add lighting or material constraints when useful.
Vorschlag · nicht geprüft
If too much of the Base Image changes, lower denoise; if the Reference Image is ignored, raise it slightly and clarify what to apply. For soft details, consider a Deblur LoRA at modest strength.
Vorschlag · nicht geprüft

Vorsichtsmaßnahmen

Before setup, check that comfyui-gguf version 1.1.5 is available in your ComfyUI installation.
Vorschlag · nicht geprüft

Muss das bearbeitet werden?

Melden Sie sich an, um eine Änderungsanfrage zu senden.

Quellen

1 Quelle

CivitaiPrimärVersion 2590009

civitai.com/models/2301814

Verifiziert 3. Nov.

Workflow instructions

Author notes from Qwen Image Edit 2511 Ultimate CIVITAI.json · selected release

If this custom node is not available to download then you can use any resize image nodes. Just make sure your image resolution is like like this - 16:9 : 1664x828 9:16 : 828x1664

Author notes from Qwen Image Edit 2511 Ultimate CIVITAI.json · selected release

Minimun steps required are 4 but you can go further. More steps = more generation time + improved result. 248364138492916 - cloth 225442473244540- 3d

Author notes from Qwen Image Edit 2511 Ultimate CIVITAI.json · selected release

# Model Links ### Diffusion Model - **Qwen-Image-Edit-2511-GGUF (GGUF)** - [Qwen-Image-Edit-2511-Q8_0.gguf](https://huggingface.co/vantagewithai/Qwen-Image-Edit-2511-GGUF/resolve/main/Qwen-Image-Edit-2511-Q8_0.gguf) ### CLIP (Text Encoder) - **Qwen 2.5 VL 7B (fp8 scaled)** - [qwen_2.5_vl_7b_fp8_scaled.safetensors](https://huggingface.co/Comfy-Org/HunyuanVideo_1.5_repackaged/resolve/main/split_files/text_encoders/qwen_2.5_vl_7b_fp8_scaled.safetensors) ### CLIP Vision - **CLIP-ViT-H-14 (laion2B)** - [CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors](https://huggingface.co/Kuvshin/models-moved/resolve/main/CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors) ### Upscaler - **Real-ESRGAN x4** - [RealESRGAN_x4.pth](https://huggingface.co/ai-forever/Real-ESRGAN/resolve/main/RealESRGAN_x4.pth) ### VAE - **Qwen Image VAE** - [qwen_image_vae.safetensors](https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/vae/qwen_image_vae.safetensors) ### LoRAs - **Qwen-Image-Edit-2511 Lightning (4 steps)** - [Qwen-Image-Edit-2511-Lightning-4steps-V1.0-bf16.safetensors](https://huggingface.co/lightx2v/Qwen-Image-Edit-2511-Lightning/resolve/main/Qwen-Image-Edit-2511-Lightning-4steps-V1.0-bf16.safetensors) - **Qwen Image Edit Deblur** - [qwen-image-edit-deblur.safetensors](https://huggingface.co/vantagewithai/Qwen_Image_Edit_LoRAs/resolve/main/qwen-image-edit-deblur.safetensors) - **CivitAI LoRA #1** - [Model 2105899 (SafeTensor)](https://civitai.com/api/download/models/2105899?type=Model&format=SafeTensor) - **CivitAI LoRA #2** - [Model 2474488 (SafeTensor)](https://civitai.com/api/download/models/2474488?type=Model&format=SafeTensor) ## ComfyUI Directory Layout Place the downloaded files into the following folders: 📂 `ComfyUI/` ├── 📂 `models/` │ ├── 📂 `text_encoders/` │ │ └── `qwen_2.5_vl_7b_fp8_scaled.safetensors` │ ├── 📂 `loras/` │ │ ├── `Qwen-Image-Edit-2511-Lightning-4steps-V1.0-bf16.safetensors` │ │ ├── `qwen-image-edit-deblur.safetensors` │ │ ├── *(CivitAI LoRA #1 you download)* │ │ └── *(CivitAI LoRA #2 you download)* │ ├── 📂 `diffusion_models/` │ │ └── `Qwen-Image-Edit-2511-Q8_0.gguf` │ └── 📂 `vae/` │ └── `qwen_image_vae.safetensors` ### Extra (Recommended) Folders 📂 `ComfyUI/` ├── 📂 `models/` │ ├── 📂 `clip_vision/` │ │ └── `CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors` │ └── 📂 `upscale_models/` │ └── `RealESRGAN_x4.pth`

Author notes from Qwen Image Edit 2511 Ultimate CIVITAI.json · selected release

Increase/Decrease threshold for best result. Or disable this node for other edits Enable only when image is too complicated.