Koan-Sin Tan
Koan-Sin Tan
@anhappdev I didn't realize it's in "public testing" now. Could we back to "internal testing" because we don't have the EULA fixed and all the backends tested.
@mohitmundhragithub to test [build 136](https://github.com/mlcommons/mobile_app_open/actions/runs/9204383464) and [build 134](https://github.com/mlcommons/mobile_app_open/actions/runs/9202794767)
Android API Level 30 means Android 11, https://developer.android.com/tools/releases/platforms#11, I think that's fine. @mohitmundhragithub and @AhmedTElthakeb or @Mostelk, what do you think?
from Inference group task summary slide: https://docs.google.com/presentation/d/1jHuhzyo_4zR1gjIsAxMywpDDN_D7H0mG0CoPqkPi3PU/edit?usp=drive_link - Model - Model: Stable Diffusion XL Base 1.0 (SDXL) without refiner - stabilityai/stable-diffusion-xl-base-1.0 - Negative prompt: - normal quality, low quality, worst...
@mohitmundhragithub please check if you need more information For mobile device, we should start from 1. Stable Diffusion 1.5 (or 1.4 when 1.5 tflite files not ready) 2. output image...
more on stable diffusion - there are 3 models - Text encoder: strings needed to be encoded with BPE first. - diffusion model: take output from the encoder + RNG...
@Mostelk With the [AI Edge Torch](https://github.com/google-ai-edge/ai-edge-torch/), a tool that can convert PyTorch models directly to TFLite, I managed to convert [HuggingFace SD 1.5 ](https://huggingface.co/runwayml/stable-diffusion-v1-5)Unet to saved_model and tflite. The tool...
Converting Stable Diffusion 1.5 Text Encoder and Unet to TFLite, https://colab.research.google.com/drive/11S1LM9S0eHO22VF3-AgOJJXJ9jNXr-ZN?usp=sharing.
> > Converting Stable Diffusion 1.5 Text Encoder and Unet to TFLite, https://colab.research.google.com/drive/11S1LM9S0eHO22VF3-AgOJJXJ9jNXr-ZN?usp=sharing. > > Freedom, unable to access the link. Possible to share in some google drive location? access...
> Hi @freedomtan Thanks. We were able to convert the encoder and Unet to tflite versions. What about the VAE decoder from the SDpipeline. Any limitations in converting them or...