AznamirWoW

Results 14 issues of AznamirWoW

1) Install pre-requisites: a) HIP SDK 6.1.2 https://www.amd.com/en/developer/resources/rocm-hub/hip-sdk.html b) Zluda 3.8 https://github.com/lshqqytiger/ZLUDA/releases/tag/rel.86cdab3b14b556e95eafe370b8e8a1a80e8d093b c) if using GPU unsupported by HIP SDK, such as 6600/6700(XT) need to find/build a custom set of...

enhancement
in progress

Elevelabs-TTS works only with the current GIT build, but returns an error Voice conversion failed: 'hubert' the reason is that /rvc/lib/utils.py does not have "hubert" entry in load_embeddings function embedding_list...

### Issue Description Open img2img. On the image tab load an image of a fox face, provide a prompt "a red fox". Click Edit button, see this: ![image](https://github.com/user-attachments/assets/8bf69907-8e50-48c3-8851-3fcc7bc5c20e) 1) mouse...

backlog

### Issue Description Open the image tab, load an image of a fox face, provide a prompt "a red fox", select the outpainting parameters - 256 pixels, down. Expected results:...

### Feature description Right now VAE selection under 'Execution & Models' settings applies to all models, so while a user may pick 'fixFP16ErrorsSDXLLowerMemoryUse_v10.safetensors' for SDXL models, SD1.5 or other do...

enhancement

**To Reproduce** 1) train a new voice model using a single 3 sec silent audio file, 1 epoch. Run inference on the same 3 sec silent audio using the model...

bug
question

Added Zluda hijacks required to avoid exceptions and added a generate from text file option **Is this PR adding new feature or fix a BUG?** Add feature **Is this pull...

While the attempt to use iSTFT to avoid upscaling artifacts introduced by last two upscales in HiFiGAN is commendable, it just does not work. On a single sample the model...

**Apr 24 update** Install Cuda Toolkit 12.8 from Applio's folder start a command line, then run ``env\python -m pip install torch==2.7.0 torchvision==0.22.0 torchaudio==2.7.0 --upgrade --index-url https://download.pytorch.org/whl/cu128``

enhancement