captainzz

咨询MPP解码block模式

12

您好， 我现在在使用Mpp进行解码，实时的往解码器里喂码流，想要设置block模式，设置了INPUT BLOCK和OUTPUT BLOCK如下： ` RK_U32 block = -1; mpi_cmd = MPP_SET_OUTPUT_BLOCK_TIMEOUT; param = █ ret = pDecCtx_mpp->mpi->control(pDecCtx_mpp->ctx, mpi_cmd, param); if(ret != MPP_OK){ WLog_DBG(TAG,"MPP_SET_OUTPUT_BLOCK ret=%d, ctx=%p",ret, pDecCtx_mpp->ctx); } mpi_cmd =...

fix mask_image in test_brushnet.py

1

# What does this PR do? Hi, I have tested SD-1.5 with "examples\brushnet\test_brushnet.py", but i found that the results were not as same as the results in folder "examples\brushnet\src". I...

Hi, I was tried to enable T-GATE for controlnet, but it always had errors and couldn't run successfully, i want to ask if you have the plan to support T-GATE...

🐛 [Bug] SDv1.5 generate black image with torch_tensorrt compile

3

## Bug Description SDv1.5 generate black image with torch_tensorrt compile log on cmd: Lib\site-packages\diffusers\image_processor.py:97: RuntimeWarning: invalid value encountered in cast images = (images * 255).round().astype("uint8") Potential NSFW content was detected...

Hi, Awesome project! Is there any recommendations of img2img text generation? For example, I want to add some text to a specific image by using diffusion model. Is there some...

### Describe the bug I trained BrushNet with BrushData, but some values of BrushData (e.g. width, height or segmentation) is missing, so the training is broken in dataloader process, is...

NPU inference error

6

Hi, I am interested in the NPU inference for this project. I tried to run llama on NPU with python\llm\example\NPU\HF-Transformers-AutoModels\Model\llama2\generate.py. I used interface `model.save_low_bit` and `AutoModelForCausalLM.load_low_bit` to save and load...