High quality image editing no longer needs closed models
We release FLUX.1 Kontext [dev] - an open weights model for proprietary-level image editing performance. Runs on consumer chips.
✓ Open weights available
✓ Best in-class performance
✓ Self-serve commercial licensing
Purpose-built for image editing: FLUX.1 Kontext [dev] enables iterative editing, excels at character preservation across diverse scenes & allows precise local and global edits.
Shares architecture with FLUX.1 [dev] = minimal code changes for inference.
Available on @github
We collaborate with @NVIDIA_AI_PC and release optimized weights for NVIDIA Blackwell
✓ TensorRT optimized weights
✓ bf16, fp8, fp4 variants
✓ Faster inference, less memory
Available @huggingface
inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
Why it matters
You can self-host iterative image editing with character preservation instead of paying per call to a closed API, and the commercial license is self-serve rather than a sales conversation.
Read the full thread on X ↗
