t01nstyle LoRA for Qwen-Image-Edit-2509
Style LoRA trained in T2I mode (--model_version original) on Qwen-Image-Edit-2509 weights.
Loads on the full Qwen-Image-Edit-2509 pipeline at inference.
Trigger: t01nstyle
Recommended inference setup:
- Pipeline: Qwen-Image-Edit-2509 (multi-reference + ControlNet pose stack)
- LoRA scale: 0.7β0.9 (not 1.0 β preserves identity from reference images)
- Sampler: FlowMatch / Euler, 25β40 steps
- True CFG: 4.0
- Resolution: 1024Β² or native 1328Β²
Training:
- Tuner: musubi-tuner (kohya-ss),
--model_version original - Dataset: 256 art targets in t01nstyle, captions only (no control images)
- Network rank/alpha: 32 / 32
- Learning rate: 1e-4 (adamw8bit, constant_with_warmup, 200 warmup steps)
- Timestep sampling: shift, discrete_flow_shift 2.2, num_timestep_buckets 4
- 30 epochs, ~4,140 steps
- Hardware: H100 SXM 80GB
Why T2I mode on an Edit model: training in T2I mode (without control images) gives the LoRA a clean style-only signal. At inference on the Edit pipeline, ControlNet handles pose, multi-reference handles identity, and this LoRA only handles style β no conflicts between components.
Checkpoints provided: epochs 12β28 (every 2 epochs) + final (epoch 30). Best checkpoint typically around epochs 18β25.
Inference Providers NEW
This model isn't deployed by any Inference Provider. π Ask for provider support
Model tree for KassandraToon/t01nstyle-qie2509-lora
Base model
Qwen/Qwen-Image-Edit-2509