Views
No views yet
model_index.json: pipeline/component registry (RSEditModifiedDiTPipeline).pipeline.py: custom local pipeline implementation used for inference/loading.checkpoint-30000/: training-state snapshot at step 30k (optimizer/scheduler/random state plus transformer weights).transformer/, vae/, text_encoder/, tokenizer/, scheduler/: exported model components for direct pipeline loading.logs/: experiment logs (logs/rsedit-dit/...).1from diffusers import DiffusionPipeline
2
3model_dir = "datasets/my_running_checkpoints/RSEdit-DiT-Modified-NoWindow-RoPE-QKNorm-SEG"
4pipe = DiffusionPipeline.from_pretrained(model_dir, trust_remote_code=True)
5pipe = pipe.to("cuda")checkpoint-30000/optimizer.bin is large and mainly needed for training resume, not standard inference.checkpoint-30000/transformer_ema/ exists for EMA tracking during training workflows.pipeline.py and model_index.json aligned if the custom pipeline class changes.