open-mmlab/mmagic
OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox. Unlock the magic 🪄: Generative-AI (AIGC), easy-to-use APIs, awsome model zoo, diffusion models, for text-to-image generation, image/video restoration/enhancement, etc.
Jupyter NotebookApache-2.0
Issues
- 2
['AsymmetricAutoencoderKL is already registered in model at mmagic.models.archs']
#2133 opened by Maxibugg - 9
No module named 'diffusers.pipelines.controlnet_xs'
#2110 opened by Winnie202 - 1
- 1
文生图Demo执行后output图片生成不出来[Bug]
#2137 opened by learner-dhx - 1
[Bug] linux环境,运行视频超分程序,中断
#2131 opened by Danny0802 - 0
Too long data_time in training of denoise and deblur models. And too low GPU utilization
#2130 opened by GeLeinjust - 0
[Bug] BasicVSR++ epoch display
#2128 opened by pingxingxianpaixingxing - 1
[Bug] Can not work
#2125 opened by ZeeLyn - 0
[Bug] CUBLAS_STATUS_EXECUTION_FAILED error for BasicVSR_PP for tasks with resolutions >~1700x1080
#2124 opened by jacob-stein - 2
[Bug] When using resmue to continue training, AssertionError: If capturable=False, state_steps should not be CUDA tensors. occurs
#1988 opened by zdyshine - 0
[Bug] When I RUN the "QUICK RUN" in the documentation, something goes wrong
#2122 opened by slantingsun - 2
[Bug] cyclegan:UnboundLocalError: local variable 'init_info' referenced before assignment
#2109 opened by xvjiawen - 0
- 0
[Feature] PowerPaint training code
#2090 opened by okotaku - 0
[Bug] Can not use `ConcatImageVisualizer` in train step. / 在Train阶段可视化存在bug
#2118 opened by Pengyang233 - 2
torch.cuda.OutOfMemoryError: CUDA out of memory.real_basicvsr/basicvsr++运行报错
#2117 opened by txy00001 - 1
[Docs] BasicVSR++
#2116 opened by txy00001 - 0
[Bug] - ImportError: /opt/conda/envs/mmagic/lib/python3.9/site-packages/mmcv/_ext.cpython-39-x86_64-linux-gnu.so: undefined symbol: _ZN3c105ErrorC2ENS_14SourceLocationESs
#2115 opened by Joish - 1
[Bug] Dockerfile error
#2070 opened by limhasic - 7
Outpainting of PowerPaint
#2083 opened by superhero-7 - 2
[Bug] no file of configs/animatediff/animatediff.py
#2106 opened by JoshonSmith - 0
[Docs] The link MMEditing in the README redirects back to the same mmagic page
#2108 opened by yurivict - 0
[Bug] RealBasic got killed when loading model
#2107 opened by IceWind233 - 0
[Bug] NSFW Error
#2104 opened by Echolink50 - 0
PowerPaint Windows MMCV Error?
#2100 opened by Echolink50 - 1
- 2
I followed the official installation tutorial and tried 3 times to keep this error
#2025 opened by tl31707chy - 0
PowerPaint Windows MMCV Error
#2099 opened by Echolink50 - 0
[Feature] Give model different intialization
#2097 opened by jS5t3r - 0
[Bug] Invalid 'input_ids' in position:0 to 75.Expect'[49428,49429,49430,49431,49432,49433,49434,49435,49436,49437] for embedding 'P_obj' but found '[49428,49407]'
#2096 opened by shineway14 - 2
- 1
When I run python gradio_PowerPaint.py, it looks for a .bin file in models/unet folder. But the model is a .safetensors file, changing the extension to .bin causes a pickle error. Any workaround?[Bug]
#2089 opened by alexbespik - 2
[Feature] PowerPaint Context-aware Image Inpainting demo
#2087 opened by okotaku - 0
- 0
How to save images one by one during inference in VSR[Docs]
#2074 opened by Lipurple - 0
any working pipeline for biggan?
#2073 opened by sipie800 - 0
- 0
- 0
- 0
Name change[Docs]
#2065 opened by wym1233 - 0
[Bug] latents = 1 / 0.18215 * latents is wrong in models/editor/stable-diffusion-xl.py
#2062 opened by LoveU3tHousand2 - 0
train stable diffusion with lora
#2049 opened by hust-kevin - 0
[Bug]
#2044 opened by maoqiuerer - 2
RTX3090 run video spuer resulotion inference error
#2032 opened by Git-Digger - 0
[Bug][Controlnet Animation]control_detector in anythingv3_config.py should be 'lllyasviel/Annotators'
#2024 opened by dai-ichiro - 0
super-large images(10000*10000) problem
#2022 opened by XuanjiaZ - 0
Can video hyperprocessors, such as realbasicvsr, only use sequence images instead of video when testing? In addition, is there a size limit for the image as input? Can the image of super size (such as 10000*10000) be directly used as input? If you can not directly as input, then how to modify the code to achieve large image input[Feature]
#2020 opened by XuanjiaZ - 20
[Bug]
#1993 opened by mycomedico - 3
[Bug] raise ValueError(f'Unknown inferencer task: {self.task}') ValueError: Unknown inferencer task: Text2Image, Inpainting
#1992 opened by hs756149694 - 3
How to use y channel training[Bug]
#1989 opened by 11923303233