psydok

Am I right, are you suggesting to convert the model to onnx using the built in `model.export("model.onnx")` method and then call `torch.jit.script` on the onnx?

I have train_ds installed. It is not possible to restore training with the same lr, either restarts or min_lr ``` train_ds: manifest_filepath: "../manifest.json" labels: ${model.labels} sample_rate: ${model.sample_rate} batch_size: &batch_size 16...

Strangely `max_steps` is always set, but sometimes lr starts from min_lr, sometimes from where it left off. Maybe I'm starting the wrong way to start retraining my models? Tell me,...

@JoeyLearnsToCode @greasebig can you tell me if the problem has been solved?

@DenOfEquity @lllyasviel Can you please tell me if there is any workaround to make [PuLID-FLUX](https://huggingface.co/spaces/yanze/PuLID-FLUX) work in Forge?

What version is fix in? 0.3.5? I'm using version 0.3.0. Same error.

@polodealvarado @vijayendra-g I have encountered the same problem. Onnx runs 2 times longer than the normal model. It was written that the fixes thread has the needed fix, but that...

@polodealvarado Thank you for your answer! I conducted experiment: I limited the sequence to 512. The response time of the model actually got better, but the results are about the...

The default value is `model.config.max_len #= 384` I tried more models from onnx-community. Either the quality is terrible, or the original model is already there... https://huggingface.co/onnx-community/gliner_multi

Also, it seems like sd_model_checkpoint is being ignored... `"override_settings": {"sd_model_checkpoint": "dreamshaper_v8.safetensors"},`