WorkflowPrésentéExterne

Qwen Image Workflow — 2512V1

(This is not an exhaustive changelog)

TâcheMise à l'échelleFamilleQwen-ImageVersionRelease 2556299 — QwenImage2512V1.jsonEstimé VRAMNot yet characterizedUnratedClasse

Profil d'exécution

Description de la source

Upload of V1

(This is not an exhaustive changelog)

Added V1:

Wildcard support

Upscale

AuraFlow Model Shift

Image Saver with Metadata

LoRA Loader

Detailer

Multipass

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

Exigences

4x_foolhardy_Remacri.pth
Dépôt identifiéOptionnel
Upscaler · Hugging Face · FacehugmanIII/4x_foolhardy_Remacri
face_yolov9c.pt
Fichier indiquéOptionnel
Object Detector · 49.3 MB · Hugging Face · Bingsu/adetailer
qwen_2.5_vl_7b_fp8_scaled.safetensors
Fichier indiqué
Text encoder · 8.74 GB · Hugging Face · Comfy-Org/Qwen-Image_ComfyUI
qwen_image_vae.safetensors
Dépôt identifié
VAE · Hugging Face · Comfy-Org/Qwen-Image_ComfyUI
qwen-image-2512-Q8_0.gguf
Non résolu
Diffusion model · Hugging Face · unsloth/Qwen-Image-2512-GGUF
sam_vit_b_01ec64.pth
Dépôt identifiéOptionnel
Segmentation · Unknown
Wuli-Qwen-Image-2512-Turbo-LoRA-4steps-V1.0-bf16_ComfyUi.safetensors
Dépôt identifié
LoRA · Hugging Face · Wuli-art/Qwen-Image-2512-Turbo-LoRA

Commentaire généré par l’IA

Explication générée par l’IA à partir des détails de la source et de la configuration. Les suggestions sont clairement signalées.

Qwen Image Workflow is for generating Qwen images in ComfyUI: it uses a diffusion model, text encoder, and VAE, takes the listed model files and image-size choices, and includes ComfyUI-Image-Saver for saving the resulting images.

The workflow combines the diffusion model, text encoder, and VAE, with optional components listed for Turbo LoRA, upscaling, face detection, and SAM segmentation.
ComfyUI-Image-Saver is listed for saving image outputs.

Available aspect ratios are 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, and 2:3.
The corresponding listed image sizes are 1328 × 1328, 1664 × 928, 928 × 1664, 1472 × 1104, 1104 × 1472, 1584 × 1056, and 1056 × 1584, in the same order.

Place qwen-image-2512-Q8_0.gguf in ComfyUI/models/diffusion_models, qwen_2.5_vl_7b_fp8_scaled.safetensors in ComfyUI/models/text_encoders, and qwen_image_vae.safetensors in ComfyUI/models/vae.
Suggestion · non vérifié
Install ComfyUI-Manager, rgthree-comfy, ComfyUI-Easy-Use, ComfyUI-Image-Saver, ComfyUI-Impact-Pack, and ComfyUI-Impact-Subpack.
Suggestion · non vérifié

Required model files are qwen-image-2512-Q8_0.gguf, qwen_2.5_vl_7b_fp8_scaled.safetensors, and qwen_image_vae.safetensors.
Optional model files listed are Wuli-Qwen-Image-2512-Turbo-LoRA-4steps-V1.0-bf16_ComfyUi, 4x_foolhardy_Remacri.pth, face_yolov9c.pt, and sam_vit_b_01ec64.pth.
The listed custom nodes are ComfyUI-Manager, rgthree-comfy, ComfyUI-Easy-Use, ComfyUI-Image-Saver, ComfyUI-Impact-Pack, and ComfyUI-Impact-Subpack; comfyui-gguf is also listed.

The listed settings are 4 steps with LoRA, CFG 1.0 with LoRA, the Euler sampler, and the Simple scheduler.
The listed image sizes are 1328 × 1328 for 1:1, 1664 × 928 for 16:9, 928 × 1664 for 9:16, 1472 × 1104 for 4:3, 1104 × 1472 for 3:4, 1584 × 1056 for 3:2, and 1056 × 1584 for 2:3.

Before use, verify that the exact required model files are in the specified ComfyUI folders.
Suggestion · non vérifié
Verify the exact file or package for qwen-image-2512-Q8_0.gguf, qwen_image_vae.safetensors, 4x_foolhardy_Remacri.pth, face_yolov9c.pt, sam_vit_b_01ec64.pth, and comfyui-gguf before relying on those parts.
Suggestion · non vérifié

Faut-il modifier cela ?

Connectez-vous pour envoyer une demande de modification.

Sources

1 source

CivitaiPrincipalVersion 2556299

Vérifié 3 nov.