T5B/Qwen-Image-Layered-FP8
Full fine-tune vs Qwen/Qwen-Image-Layered. Fine-tune: 100% of the weights changed, across 0 of 0 layers.
Tensors changed: other 123/246, Embeddings 0/5, Attention 480/960, Norms 0/243, MLP 240/480
Full fine-tune vs Qwen/Qwen-Image-Layered. Fine-tune: 100% of the weights changed, across 0 of 0 layers.
Tensors changed: other 123/246, Embeddings 0/5, Attention 480/960, Norms 0/243, MLP 240/480