uminosachi / inpaint-anything Goto Github PK

Hi, thank you for your great work.
I wonder if you can add an option to disable the automatic save feature to this extension. I will save it myself if needed (usually, I only want to use the mask for the inpainting function).

运行 Inpaint Anything 总是报内存不足，没有一次成功的，R5 3600 3060ti RAM16G 是不是这个卡无法运行这个插件，
2024-02-03 20:39:53,872 - Inpaint Anything - ERROR - Allocation on device 0 would exceed allowed memory. (out of memory)
Currently allocated : 3.26 GiB
Requested : 2.64 GiB
Device limit : 8.00 GiB
Free (according to CUDA): 0 bytes
PyTorch limit (set by user-supplied memory fraction)
: 17179869184.00 GiB

WARNING:huggingface_hub.utils._http:'HTTPSConnectionPool(host='huggingface.co', port=443): Max retries exceeded with url: /Uminosachi/realisticVisionV51_v51VAE-inpainting/resolve/main/model_index.json (Caused by ConnectTimeoutError(<urllib3.connection.HTTPSConnection object at 0x000002219323F6A0>, 'Connection to huggingface.co timed out. (connect timeout=10)'))' thrown while requesting HEAD https://huggingface.co/Uminosachi/realisticVisionV51_v51VAE-inpainting/resolve/main/model_index.json
2024-01-17 10:37:39,215 - Inpaint Anything - ERROR - We have no connection or you passed local_files_only, so force_download is not an accepted option.

Hey, Thanks for your project!
I want to create absolutereality_v181INPAINTING.safetensors model for inpainting. I don't know how to create custom models to Huggingface. You mentioned here but I am new to this. So, is there any tutorial to create custom models like yours or can you please guide me how to create and which platform? and I don't want to use in SD WebUI Extension. I want in standalone version of Inpaint!

The requirements.txt file specifies torch==2.0.1. but may be better just to specify torch without locking it into a version number.

For example, I downloaded juggernautxlinpaint from civitai and would like to experiment with that and others.

I tried placing it into the models directory but it didn't do anything, I then tried placing it into the huggingface cache but it also didnt show up in the programs drop down menu, I found the file ia_ui_items.py and ran it but that didnt seem to change anything.

I then modified it trying to force it to rescan the cache using the following code:

from huggingface_hub import scan_cache_dir

def get_inp_model_ids():

    hf_cache_info = scan_cache_dir()
    inpaint_repos = []
    for repo in hf_cache_info.repos:
        if repo.repo_type == "model" and "inpaint" in repo.repo_id.lower() and repo.repo_id not in model_ids:
            inpaint_repos.append(repo.repo_id)
    inp_list_from_cache = sorted(inpaint_repos, reverse=True, key=lambda x: x.split("/")[-1])
    model_ids.extend(inp_list_from_cache)
    return model_ids

    return model_ids

and it seemed to run without errors, but I refreshed/relaunched and nothing changes it.

How do I add custom models to the programs?
Is there a directory in the program I need to add my own folder to? And what should it be named.

This tool would be great for selecting parts of the image and then saving as a PNG with the unmasked parts treated as transparent. Would it be possible to add this transparency feature?

Can inpaint-anything support API

Im getting a CUDA out of memory error with continual inpainting and segmenting. seems to build up VRAM usage and not release it. here it is stuck at 1/20 and continually eating up more ram, over 50gb.

Can GroundingDINO be supported like sd-webui-segment-anything

╰─ pip install diffusers
Requirement already satisfied: diffusers in c:\users\administrator\miniconda3\lib\site-packages (0.16.1)
Requirement already satisfied: Pillow in c:\users\administrator\miniconda3\lib\site-packages (from diffusers) (9.5.0)
Requirement already satisfied: filelock in c:\users\administrator\miniconda3\lib\site-packages (from diffusers) (3.12.4)
Requirement already satisfied: huggingface-hub>=0.13.2 in c:\users\administrator\miniconda3\lib\site-packages (from diffusers) (0.17.3)
Requirement already satisfied: importlib-metadata in c:\users\administrator\miniconda3\lib\site-packages (from diffusers) (6.8.0)
Requirement already satisfied: numpy in c:\users\administrator\miniconda3\lib\site-packages (from diffusers) (1.26.0)
Requirement already satisfied: regex!=2019.12.17 in c:\users\administrator\miniconda3\lib\site-packages (from diffusers) (2023.8.8)
Requirement already satisfied: requests in c:\users\administrator\miniconda3\lib\site-packages (from diffusers) (2.29.0)
Requirement already satisfied: fsspec in c:\users\administrator\miniconda3\lib\site-packages (from huggingface-hub>=0.13.2->diffusers) (2023.9.2)
Requirement already satisfied: tqdm>=4.42.1 in c:\users\administrator\miniconda3\lib\site-packages (from huggingface-hub>=0.13.2->diffusers) (4.66.1)
Requirement already satisfied: pyyaml>=5.1 in c:\users\administrator\miniconda3\lib\site-packages (from huggingface-hub>=0.13.2->diffusers) (6.0.1)
Requirement already satisfied: typing-extensions>=3.7.4.3 in c:\users\administrator\miniconda3\lib\site-packages (from huggingface-hub>=0.13.2->diffusers) (4.8.0)
Requirement already satisfied: packaging>=20.9 in c:\users\administrator\miniconda3\lib\site-packages (from huggingface-hub>=0.13.2->diffusers) (23.0)
Requirement already satisfied: zipp>=0.5 in c:\users\administrator\miniconda3\lib\site-packages (from importlib-metadata->diffusers) (3.17.0)
Requirement already satisfied: charset-normalizer<4,>=2 in c:\users\administrator\miniconda3\lib\site-packages (from requests->diffusers) (2.0.4)
Requirement already satisfied: idna<4,>=2.5 in c:\users\administrator\miniconda3\lib\site-packages (from requests->diffusers) (3.4)
Requirement already satisfied: urllib3<1.27,>=1.21.1 in c:\users\administrator\miniconda3\lib\site-packages (from requests->diffusers) (1.26.16)
Requirement already satisfied: certifi>=2017.4.17 in c:\users\administrator\miniconda3\lib\site-packages (from requests->diffusers) (2023.5.7)
Requirement already satisfied: colorama in c:\users\administrator\miniconda3\lib\site-packages (from tqdm>=4.42.1->huggingface-hub>=0.13.2->diffusers) (0.4.6)

what the title says ......................

How can I use Loras with inpaint?

hello, so I found this extension through youtube and I'm interested to try it out. So I've downloaded the model, I've inserted the image but when I fill the prompt in Inpaint and click run inpainting it only gives masked area as an output.

1. Model
   

2. Inpaint prompt + Mask selection
   
   

3. Result + CMD
   
   

Please help, am I missing something?

Where is the resize mode option?

Is there a fix for this? I tried to add Loras but this shows up in my terminal!

Running A1111 in Stability Matrix and while inPaint Anything is listed as a TAB, on another computer it fails to show up.

How can I fix this?

CPU: i9 13900k
GPU:4090
I follow the GitHub tutorial, but in the last step "Run inpainting" after a few min loading, it show error message. please someone help thank you so much.

error message below.

Running on local URL: http://127.0.0.1:7860

To create a public link, set share=True in launch().
input_image: (4000, 6000, 3) uint8
SamAutomaticMaskGenerator sam_vit_b_01ec64.pth
SAM processing time: 124.52666926383972
Uminosachi/dreamshaper_6Inpainting
Downloading (…)ain/model_index.json: 100%|█████████████████████████████████████████████████████████| 579/579 [00:00<00:00, 1.15MB/s]
text_encoder\model.safetensors not found
Downloading (…)cheduler_config.json: 100%|█████████████████████████████████████████████████████████████████| 460/460 [00:00<?, ?B/s]
Downloading (…)rocessor_config.json: 100%|█████████████████████████████████████████████████████████████████| 520/520 [00:00<?, ?B/s]
Downloading (…)_checker/config.json: 100%|█████████████████████████████████████████████████████| 4.58k/4.58k [00:00<00:00, 4.59MB/s]
Downloading (…)_encoder/config.json: 100%|█████████████████████████████████████████████████████████████████| 612/612 [00:00<?, ?B/s]
Downloading (…)cial_tokens_map.json: 100%|█████████████████████████████████████████████████████████████████| 472/472 [00:00<?, ?B/s]
Downloading (…)okenizer_config.json: 100%|█████████████████████████████████████████████████████████| 737/737 [00:00<00:00, 1.47MB/s]
Downloading (…)6c9/unet/config.json: 100%|█████████████████████████████████████████████████████| 1.55k/1.55k [00:00<00:00, 2.60MB/s]
Downloading (…)tokenizer/merges.txt: 100%|████████████████████████████████████████████████████████| 525k/525k [00:00<00:00, 931kB/s]
Downloading (…)e6c9/vae/config.json: 100%|█████████████████████████████████████████████████████████████████| 577/577 [00:00<?, ?B/s]
Downloading (…)tokenizer/vocab.json: 100%|█████████████████████████████████████████████████████| 1.06M/1.06M [00:00<00:00, 1.34MB/s]
Downloading pytorch_model.bin: 100%|█████████████████████████████████████████████████████████████| 246M/246M [00:20<00:00, 11.9MB/s]
Downloading (…)on_pytorch_model.bin: 100%|███████████████████████████████████████████████████████| 167M/167M [00:29<00:00, 5.67MB/s]
Downloading pytorch_model.bin: 100%|█████████████████████████████████████████████████████████████| 608M/608M [00:46<00:00, 13.1MB/s]
Downloading (…)on_pytorch_model.bin: 100%|█████████████████████████████████████████████████████| 1.72G/1.72G [01:55<00:00, 14.9MB/s]
Fetching 15 files: 100%|████████████████████████████████████████████████████████████████████████████| 15/15 [01:57<00:00, 7.83s/it]
C:\Users\user\anaconda3\envs\inpaint\lib\site-packages\transformers\models\clip\feature_extraction_clip.py:28: FutureWarning: The class CLIPFeatureExtractor is deprecated and will be removed in version 5 of Transformers. Please use CLIPImageProcessor instead.7MB/s]
warnings.warn(n_pytorch_model.bin: 100%|█████████████████████████████████████████████████████| 1.72G/1.72G [01:55<00:00, 21.3MB/s]
The config attributes {'addition_embed_type': None, 'addition_embed_type_num_heads': 64, 'class_embeddings_concat': False, 'cross_attention_norm': None, 'encoder_hid_dim': None, 'mid_block_only_cross_attention': None, 'resnet_out_scale_factor': 1.0, 'resnet_skip_time_act': False, 'time_embedding_act_fn': None, 'time_embedding_dim': None} were passed to UNet2DConditionModel, but are not expected and will be ignored. Please verify your config.json configuration file.
Using sampler DDIM
Traceback (most recent call last):
File "C:\Users\user\anaconda3\envs\inpaint\lib\site-packages\gradio\routes.py", line 427, in run_predict
output = await app.get_blocks().process_api(
File "C:\Users\user\anaconda3\envs\inpaint\lib\site-packages\gradio\blocks.py", line 1323, in process_api
result = await self.call_function(
File "C:\Users\user\anaconda3\envs\inpaint\lib\site-packages\gradio\blocks.py", line 1051, in call_function
prediction = await anyio.to_thread.run_sync(
File "C:\Users\user\anaconda3\envs\inpaint\lib\site-packages\anyio\to_thread.py", line 33, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
File "C:\Users\user\anaconda3\envs\inpaint\lib\site-packages\anyio_backends_asyncio.py", line 877, in run_sync_in_worker_thread
return await future
File "C:\Users\user\anaconda3\envs\inpaint\lib\site-packages\anyio_backends_asyncio.py", line 807, in run
result = context.run(func, *args)
File "C:\Researchteam\Inpainting anything\inpaint-anything\iasam_app.py", line 465, in run_inpaint
pipe.enable_xformers_memory_efficient_attention()
File "C:\Users\user\anaconda3\envs\inpaint\lib\site-packages\diffusers\pipelines\pipeline_utils.py", line 1080, in enable_xformers_memory_efficient_attention
self.set_use_memory_efficient_attention_xformers(True, attention_op)
File "C:\Users\user\anaconda3\envs\inpaint\lib\site-packages\diffusers\pipelines\pipeline_utils.py", line 1105, in set_use_memory_efficient_attention_xformers
fn_recursive_set_mem_eff(module)
File "C:\Users\user\anaconda3\envs\inpaint\lib\site-packages\diffusers\pipelines\pipeline_utils.py", line 1096, in fn_recursive_set_mem_eff
module.set_use_memory_efficient_attention_xformers(valid, attention_op)
File "C:\Users\user\anaconda3\envs\inpaint\lib\site-packages\diffusers\models\modeling_utils.py", line 219, in set_use_memory_efficient_attention_xformers
fn_recursive_set_mem_eff(module)
File "C:\Users\user\anaconda3\envs\inpaint\lib\site-packages\diffusers\models\modeling_utils.py", line 215, in fn_recursive_set_mem_eff
fn_recursive_set_mem_eff(child)
File "C:\Users\user\anaconda3\envs\inpaint\lib\site-packages\diffusers\models\modeling_utils.py", line 215, in fn_recursive_set_mem_eff
fn_recursive_set_mem_eff(child)
File "C:\Users\user\anaconda3\envs\inpaint\lib\site-packages\diffusers\models\modeling_utils.py", line 215, in fn_recursive_set_mem_eff
fn_recursive_set_mem_eff(child)
File "C:\Users\user\anaconda3\envs\inpaint\lib\site-packages\diffusers\models\modeling_utils.py", line 212, in fn_recursive_set_mem_eff
module.set_use_memory_efficient_attention_xformers(valid, attention_op)
File "C:\Users\user\anaconda3\envs\inpaint\lib\site-packages\diffusers\models\attention.py", line 104, in set_use_memory_efficient_attention_xformers
raise ValueError(
ValueError: torch.cuda.is_available() should be True but is False. xformers' memory efficient attention is only available for GPU