Flux-Kontext - Wan 2.2 Character Lora Training Image Generation
Details
Download Files
About this version
Model description
π§© Flux-Kontext Character Expansion Workflow
Overview
This custom Flux-Kontext workflow is a major extension of the base model, built to handle multi-image composition, LoRA stacking, and multi-step generation for high-quality, consistent character datasets.
Itβs designed for character creation, LoRA training, and regeneration of low-quality inputs β giving you complete control over appearance, context, and detail.
πΌοΈ Dual-Image Context System
The workflow allows you to combine two different input images into a single coherent generation:
If both inputs are active, the system blends their visual and semantic context β e.g., βthe man and the woman are dancing.β
If only one image is active, the model evolves that image using the new prompt β e.g., βsame face and clothes, the man is riding a horse.β
This setup enables dynamic, instruction-based image merging without losing character identity.
π§ LoRA Power Loader
A custom LoRA Power Loader lets you stack multiple LoRAs simultaneously, each with independent strength control.
You can fine-tune how each LoRA influences the output β controlling aspects like:
Facial identity
Body type and proportions
Clothing style
Lighting or artistic detail
This provides granular creative direction for dataset generation or character refinement.
π Latent Upscale & Restoration
A built-in Latent Upscale node enhances weak or low-resolution inputs before re-generation.
It restores missing structure and detail at the latent level, producing clean, high-resolution results without introducing blur or artifact noise.
Use this feature to:
Improve dataset quality
Restore bad or compressed source images
Regenerate old renders into consistent HD-quality material
π§© Multi-Prompt / Multi-Step Generation
The workflow supports multiple prompts and generation passes, automatically rendering your character in:
Different poses
Varied lighting and environments
Multiple angles and camera distances
This produces a rich, consistent dataset ideal for training LoRAs or any character model requiring 360Β° diversity and visual coherence.
π― Use Cases
Creating training data for LoRA or DreamBooth
Generating pose/lighting variation sets for the same character
Cleaning and enhancing low-quality reference material
Building consistent visual identity across scenes
βοΈ Requirements
Flux-Kontext nodes (ComfyUI Flux / Florence integration)
LoRA Power Loader node
Latent Upscale node
Any Flux-compatible base model
Optional: additional LoRAs placed in
/models/Lora/



