Dylan

icon location AI/ML Engineer passionate about multimodal AI. Extensive experience with LLMs, currently focused on mastering diffusion models.

Results 2 comments of Dylan

Question about optimal hyper parameters for training Qwen-Image-Edit-2509

> [@dylanzonix](https://github.com/dylanzonix) We have also observed similar issues: the Qwen-Image-Edit and Qwen-Image-Edit-2509 models are difficult to fine-tune, despite following exactly the same mathematical principles as Qwen-Image. If we find a...

Question about optimal hyper parameters for training Qwen-Image-Edit-2509

> Training the LoRa model for Qwen Image Edit 2509 using ModelScope significantly reduced the loss. However, training with DiffSyhtn resulted in a persistently oscillating loss. Interesting. You think the...