Consistent AI character sheets across poses and angles from a prompt and skeleton diagram.
ComfyUITemplates.com
Discover free ready-made ComfyUI templates for AI workflows.
FLUX & ByteDance-USO: Single Img2Img
ByteDance USO on FLUX unifies subject-driven and style-driven image generation in one pass.
ComfyUI Workflow: FLUX & ByteDance-USO – Single Img2Img
This ComfyUI workflow combines FLUX and ByteDance's USO (Unified Style Optimization) model to perform single-image-to-image transformations with style-aware reprocessing. It is designed for restyling, adapting, or transforming a reference image while preserving its structural composition.
Key features
- Single-image input: One reference image drives the transformation; no paired training data needed.
- Style-aware output: USO layer applies targeted style transfer without losing the subject.
- Composition preservation: Underlying structure of the input is maintained through FLUX's VAE encoding.
- Checkpoint flexible: Compatible with FLUX dev and schnell variants.
- Tunable strength: Control how much of the source image's structure vs. style is preserved per generation.
Use cases
- Restyling photography: Apply artistic styles to existing photos without redrawing the subject.
- Product visualization: Re-render product shots in different aesthetics while keeping the product recognizable.
- Concept art iteration: Generate stylistic variations of a base concept for client review.
- Brand consistency: Apply a brand's visual style to a batch of source images.
Similar listings in category
Batch-remove or add watermarks across many images with SAM, GroundingDINO, and diffusion.
Consistent AI character from any angle: PuLID-Flux faces, OpenPose, DeepSeek prompts, Flux detail.