Loading
Vous avez un workflow ComfyUI ? Obtenez une documentation lisible directement dans votre navigateur.Rendre un workflow lisible.Essayer maintenant ↗
ComfyUI LoRA Training Prep Workflow (with Flux1.d) This ComfyUI workflow is built to simplify dataset preparation for LoRA training by automating batch image upscaling and annotation with the power of Flux1.d . It...
Profil d'exécution
Description de la source
ComfyUI LoRA Training Prep Workflow (with Flux1.d) This ComfyUI workflow is built to simplify dataset preparation for LoRA training by automating batch image upscaling and annotation with the power of Flux1.d . It processes entire folders of images, leveraging Flux1.d’s advanced image generation and enhancement capabilities to upscale images with exceptional clarity and detail. After upscaling, it runs automated tagging/annotation to produce descriptive captions, saving them alongside each image for seamless LoRA training integration.
Key features:
Flux1.d Image Enhancement: Utilizes Flux1.d to upscale and refine images, ensuring high-resolution, high-fidelity training data.
Batch Processing: Handles large image sets with ease, making it ideal for dataset creation at scale.
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.
Batch Upscale and Annotator Workflow prepares LoRA training datasets from image folders by batch-upscaling images with Flux1.d and adding Florence captions or tags, producing paired image and text files.
It upscales images first, then generates captions or tags and saves the text alongside each image.
Input: image folders for batch processing. Output: upscaled images paired with caption or tag text files for LoRA training.
It is presented as a ComfyUI workflow with a drag-and-drop, modular node layout described as customizable.
Listed model files include ae.safetensors, clip_l.safetensors, t5xxl_fp16.safetensors, microsoft/Florence-2-base, flux1-dev-fp8.safetensors, and 4x_NMKD-Superscale-SP_178000_G.pth.
Listed ComfyUI node packs include comfyui_ultimatesdupscale, comfyui-custom-scripts, comfyui-kjnodes, and rgthree-comfy.
Listed node pack versions are comfyui_ultimatesdupscale 1.3.3, comfyui-custom-scripts 1.2.5, rgthree-comfy 1.0.0, and comfyui-kjnodes 1.1.4.
The listed base model is Flux.1 D.
Before setup, check whether your ComfyUI installation includes flux1-dev-fp8.safetensors, 4x_NMKD-Superscale-SP_178000_G.pth, comfyui-florence2, was-node-suite-comfyui, and was-ns.
Suggestion
Faut-il modifier cela ?
Connectez-vous pour envoyer une demande de modification.
Sources
1 sourceExtraits de sources
1 extraitSource context: 410 downloads · Type Workflows · Base model Flux.1 D
Automated Annotation: Generates captions or tags for each image (via Florence), drastically reducing manual labeling effort.
LoRA-Ready Output: Outputs neatly paired image and text files in a structure optimized for LoRA training workflows.
Fully ComfyUI-Integrated: Drag-and-drop functionality, modular node setup, and a clear visual workflow make it easy to customize.
This workflow is perfect for AI creators and LoRA trainers who want high-quality, consistent datasets while minimizing prep time.
Remaining hardware or download-size estimates are not available yet.
Exigences
Upscaler · 63.9 MB · PT · Unknown
ae.safetensors
TrouvéVAE · 320 MB · SAFETENSORS · Unknown
Text encoder · 235 MB · SAFETENSORS · Unknown
comfyui_ultimatesdupscale
Fichier non vérifiéUpscaler · Registry
flux1-dev-fp8.safetensors
PossibleCheckpoint · Unknown
Vision model · Hugging Face · microsoft/Florence-2-base
Text encoder · 9.12 GB · SAFETENSORS · Unknown
comfyui-custom-scripts
TrouvéPack de nœud · Registry
comfyui-florence2
PossiblePack de nœud · Registry
Pack de nœud · Registry
rgthree-comfy
TrouvéPack de nœud · Registry
was-node-suite-comfyui
PossiblePack de nœud · Registry
was-ns
Non résoluPack de nœud · Registry
