Vous avez un workflow ComfyUI ? Obtenez une documentation lisible directement dans votre navigateur.Rendre un workflow lisible.Essayer maintenant ↗
Added SEGS based details improver after upscaling
Profil d'exécution
Description de la source
🥁 Zenflow
Works for models based on SDXL , uncluding Pony & Illustrious
v5.0 introduce a huge (really huge, like a dinosaur ) improvement to upscaled images
Advanced saving options
Civit will now recognize the model & lora(s) you used
🟡 File needed for upscaling
Download RealESRGAN_x4plus_anime_6B.pth (click to download)
Put it in your ComfyUI\models\upscale_models folder
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.
Zenflow : Refiner & Upscaler (ComfyUI) v5.0 is for refining image details and upscaling images with SDXL-based models, including Pony and Illustrious; it can use prompts and base/refiner model choices to produce refined or upscaled images.
The refiner can adjust specific details while preserving the overall composition, such as adding more clouds to the sky.
Version v5.0 adds a SEGS-based details improver after upscaling.
The download includes two variants, Zenflow_v5_LORA.json and Zenflow_v5_TRT.json, with 26 nodes each.
Enter prompts in the dedicated prompting area and use SDXL-based models, including Pony and Illustrious.
Outputs can include refined images with targeted detail changes and upscaled images.
To enable upscaling, download RealESRGAN_x4plus_anime_6B.pth and place it in ComfyUI\models\upscale_models.
The Zenflow_v5_LORA.json variant lists comfyui-image-saver (1.9.2), comfyui-impact-pack (8.15.3), and rgthree-comfy (1.0.2505290026).
The Zenflow_v5_TRT.json variant lists comfyui_tensorrt (0.1.8), comfyui-image-saver (1.9.2), comfyui-impact-pack (8.15.3), and rgthree-comfy (1.0.2505290026).
Both variants list Zenmix_XL_v1-0.safetensors as a checkpoint.
Use the same model for the base and refiner, or use two different models to mix their styles.
The prompting area is designed to fit on screen, and advanced saving options are included so Civit will recognize the model and LoRA(s) used.
Before using the workflow, verify that Zenmix_XL_v1-0.safetensors is available in your ComfyUI setup.
Suggestion · non vérifié
If you plan to upscale, verify that RealESRGAN_x4plus_anime_6B.pth is in ComfyUI\models\upscale_models.
Suggestion · non vérifié
Faut-il modifier cela ?
Connectez-vous pour envoyer une demande de modification.
Sources
1 sourceExtraits de sources
2 extraitsSource context: 3012 downloads · Type Workflows · Base model SDXL 1.0
You're done 🎉
🟡 The refiner
A refiner can help you adjust specific details of your output while preserving the overall composition. In this simple example, I added more clouds in the sky
I used the same model for both the base and the refiner. However, you can use two different models to mix their style etc
🟡 Workflow overview (v5)
The prompting area (green) is designed to fit on your screen, so you can focus on what really matters without having to move your view every 30sec
Estimation des besoins VRAM
Estimation indisponible
Les tailles des fichiers du modèle ne sont pas encore suffisamment complètes pour calculer cette exigence.
Exigences
Exigences 4Zenmix_XL_v1-0.safetensors
Non résoluCheckpoint · Unknown
Pack de nœud · Registry
Pack de nœud · Registry
Source context: 2933 downloads · Type Workflows · Base model SDXL 1.0
Pack de nœud · Registry
