OrangeMix & MixPro Notebooks Disconnects Under 10 Minutes Consistently
Closed this issue · 3 comments
👍 AOM3_orangemixs.safetensors already downloaded.
👍 orangemix.vae.pt already downloaded.
/content/stable-diffusion-webui
fatal: No names found, cannot describe anything.
Python 3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]
Version: ## 1.4.0
Commit hash: 394ffa7b0a7fff3ec484bcd084e673a8b301ccc8
Installing requirements
Launching Web UI with arguments: --opt-sdp-attention --lowram --no-hashing --enable-insecure-extension-access --no-half-vae --disable-safe-unpickle --gradio-queue --ckpt /content/stable-diffusion-webui/models/Stable-diffusion/AOM3_orangemixs.safetensors --vae-path /content/stable-diffusion-webui/models/VAE/orangemix.vae.pt --share
No module 'xformers'. Proceeding without it.
Image Browser: ImageReward is not installed, cannot be used.
Loading weights [None] from /content/stable-diffusion-webui/models/Stable-diffusion/AOM3_orangemixs.safetensors
Running on local URL: http://127.0.0.1:7860/
preload_extensions_git_metadata for 19 extensions took 0.70s
Running on public URL: https://4099e1029036ce0944.gradio.live/
This share link expires in 72 hours. For free permanent hosting and GPU upgrades (NEW!), check out Spaces: https://huggingface.co/spaces
Startup time: 19.3s (import torch: 7.0s, import gradio: 1.1s, import ldm: 0.4s, other imports: 0.8s, load scripts: 1.5s, create ui: 1.9s, gradio launch: 6.4s).
Creating model from config: /content/stable-diffusion-webui/configs/v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Downloading (…)olve/main/vocab.json: 100% 961k/961k [00:00<00:00, 9.62MB/s]
Downloading (…)olve/main/merges.txt: 100% 525k/525k [00:00<00:00, 57.6MB/s]
Downloading (…)cial_tokens_map.json: 100% 389/389 [00:00<00:00, 1.64MB/s]
Downloading (…)okenizer_config.json: 100% 905/905 [00:00<00:00, 3.74MB/s]
Downloading (…)lve/main/config.json: 100% 4.52k/4.52k [00:00<00:00, 14.5MB/s]
Loading VAE weights from commandline argument: /content/stable-diffusion-webui/models/VAE/orangemix.vae.pt
Applying attention optimization: sdp... done.
Textual inversion embeddings loaded(7): bad-artist, bad-artist-anime, bad-hands-5, bad-image-v2-39000, bad_prompt_version2, EasyNegative, EasyNegativeV2
Model loaded in 33.5s (load weights from disk: 22.9s, create model: 5.6s, load VAE: 4.5s, calculate empty prompt: 0.2s).
Couldn't find Lora with name Rabbit (wlsdnjs950)
Couldn't find Lora with name aki
Couldn't find Lora with name 3DMM_V11
0% 0/35 [00:00<?, ?it/s]
3% 1/35 [00:04<02:26, 4.31s/it]
6% 2/35 [00:05<01:16, 2.33s/it]
9% 3/35 [00:06<00:54, 1.71s/it]
11% 4/35 [00:07<00:43, 1.40s/it]
14% 5/35 [00:08<00:36, 1.20s/it]
17% 6/35 [00:08<00:31, 1.09s/it]
20% 7/35 [00:09<00:28, 1.01s/it]
23% 8/35 [00:10<00:25, 1.06it/s]
26% 9/35 [00:11<00:23, 1.11it/s]
29% 10/35 [00:12<00:21, 1.14it/s]
31% 11/35 [00:12<00:20, 1.16it/s]
34% 12/35 [00:13<00:19, 1.18it/s]
37% 13/35 [00:14<00:18, 1.19it/s]
40% 14/35 [00:15<00:17, 1.20it/s]
43% 15/35 [00:16<00:16, 1.21it/s]
46% 16/35 [00:17<00:15, 1.21it/s]
49% 17/35 [00:17<00:14, 1.21it/s]
51% 18/35 [00:18<00:14, 1.21it/s]
54% 19/35 [00:19<00:13, 1.20it/s]
57% 20/35 [00:20<00:12, 1.19it/s]
60% 21/35 [00:21<00:11, 1.19it/s]
63% 22/35 [00:22<00:10, 1.19it/s]
66% 23/35 [00:22<00:10, 1.17it/s]
69% 24/35 [00:23<00:09, 1.18it/s]
71% 25/35 [00:24<00:08, 1.17it/s]
74% 26/35 [00:25<00:07, 1.17it/s]
77% 27/35 [00:26<00:06, 1.18it/s]
80% 28/35 [00:27<00:05, 1.19it/s]
83% 29/35 [00:28<00:05, 1.19it/s]
86% 30/35 [00:28<00:04, 1.20it/s]
89% 31/35 [00:29<00:03, 1.21it/s]
91% 32/35 [00:30<00:02, 1.21it/s]
94% 33/35 [00:31<00:01, 1.21it/s]
97% 34/35 [00:32<00:00, 1.22it/s]
100% 35/35 [00:32<00:00, 1.08it/s]
Total progress: 100% 35/35 [00:45<00:00, 1.30s/it]
{"prompt": "<lora:Rabbit (wlsdnjs950):0.8> lora:aki:0.3 lora:3DMM_V11:0.5 3d, thick eyebrows, gradient, gradient background, barefoot, standing, petite, little female, smile, \n", "all_prompts": ["<lora:Rabbit (wlsdnjs950):0.8> lora:aki:0.3 lora:3DMM_V11:0.5 3d, thick eyebrows, gradient, gradient background, barefoot, standing, petite, little female, smile, \n"], "negative_prompt": "(worst quality, low quality:1.4) Poorly Made Bad 3D, Lousy Bad Realistic, bad anatomy, bad hands, extra fingers, fewer fingers,\n", "all_negative_prompts": ["(worst quality, low quality:1.4) Poorly Made Bad 3D, Lousy Bad Realistic, bad anatomy, bad hands, extra fingers, fewer fingers,\n"], "seed": 2434781936, "all_seeds": [2434781936], "subseed": 953420483, "all_subseeds": [953420483], "subseed_strength": 0, "width": 560, "height": 1024, "sampler_name": "DPM++ SDE Karras", "cfg_scale": 6.5, "steps": 35, "batch_size": 1, "restore_faces": false, "face_restoration_model": null, "sd_model_hash": null, "seed_resize_from_w": 0, "seed_resize_from_h": 0, "denoising_strength": null, "extra_generation_params": {}, "index_of_first_image": 0, "infotexts": ["<lora:Rabbit (wlsdnjs950):0.8> lora:aki:0.3 lora:3DMM_V11:0.5 3d, thick eyebrows, gradient, gradient background, barefoot, standing, petite, little female, smile, \n\nNegative prompt: (worst quality, low quality:1.4) Poorly Made Bad 3D, Lousy Bad Realistic, bad anatomy, bad hands, extra fingers, fewer fingers,\n\nSteps: 35, Sampler: DPM++ SDE Karras, CFG scale: 6.5, Seed: 2434781936, Size: 560x1024, Model: AOM3_orangemixs, RNG: CPU, Version: ## 1.4.0"], "styles": [], "job_timestamp": "20230911015418", "clip_skip": 1, "is_using_inpainting_conditioning": false}
loading Lora /content/stable-diffusion-webui/models/Lora/Rabbit (wlsdnjs950).safetensors: SafetensorError
Traceback (most recent call last):
File "/content/stable-diffusion-webui/extensions-builtin/Lora/lora.py", line 253, in load_loras
lora = load_lora(name, lora_on_disk)
File "/content/stable-diffusion-webui/extensions-builtin/Lora/lora.py", line 162, in load_lora
sd = sd_models.read_state_dict(lora_on_disk.filename)
File "/content/stable-diffusion-webui/modules/sd_models.py", line 250, in read_state_dict
pl_sd = safetensors.torch.load_file(checkpoint_file, device=device)
File "/usr/local/lib/python3.10/dist-packages/safetensors/torch.py", line 259, in load_file
with safe_open(filename, framework="pt", device=device) as f:
safetensors_rust.SafetensorError: Error while deserializing header: MetadataIncompleteBuffer
loading Lora /content/stable-diffusion-webui/models/Lora/porforever_v1.0.safetensors: SafetensorError
Traceback (most recent call last):
File "/content/stable-diffusion-webui/extensions-builtin/Lora/lora.py", line 253, in load_loras
lora = load_lora(name, lora_on_disk)
File "/content/stable-diffusion-webui/extensions-builtin/Lora/lora.py", line 162, in load_lora
sd = sd_models.read_state_dict(lora_on_disk.filename)
File "/content/stable-diffusion-webui/modules/sd_models.py", line 250, in read_state_dict
pl_sd = safetensors.torch.load_file(checkpoint_file, device=device)
File "/usr/local/lib/python3.10/dist-packages/safetensors/torch.py", line 259, in load_file
with safe_open(filename, framework="pt", device=device) as f:
safetensors_rust.SafetensorError: Error while deserializing header: MetadataIncompleteBuffer
loading Lora /content/stable-diffusion-webui/models/Lora/3DMM_V11.safetensors: SafetensorError
Traceback (most recent call last):
File "/content/stable-diffusion-webui/extensions-builtin/Lora/lora.py", line 253, in load_loras
lora = load_lora(name, lora_on_disk)
File "/content/stable-diffusion-webui/extensions-builtin/Lora/lora.py", line 162, in load_lora
sd = sd_models.read_state_dict(lora_on_disk.filename)
File "/content/stable-diffusion-webui/modules/sd_models.py", line 250, in read_state_dict
pl_sd = safetensors.torch.load_file(checkpoint_file, device=device)
File "/usr/local/lib/python3.10/dist-packages/safetensors/torch.py", line 259, in load_file
with safe_open(filename, framework="pt", device=device) as f:
safetensors_rust.SafetensorError: Error while deserializing header: MetadataIncompleteBuffer
0% 0/35 [00:00<?, ?it/s]
3% 1/35 [00:00<00:29, 1.15it/s]
6% 2/35 [00:01<00:29, 1.13it/s]
9% 3/35 [00:02<00:28, 1.14it/s]
11% 4/35 [00:03<00:26, 1.15it/s]
14% 5/35 [00:04<00:26, 1.14it/s]
17% 6/35 [00:05<00:25, 1.14it/s]
20% 7/35 [00:06<00:24, 1.15it/s]
23% 8/35 [00:06<00:23, 1.15it/s]
26% 9/35 [00:07<00:22, 1.15it/s]
29% 10/35 [00:08<00:21, 1.15it/s]
31% 11/35 [00:09<00:20, 1.14it/s]
34% 12/35 [00:10<00:20, 1.15it/s]
37% 13/35 [00:11<00:19, 1.12it/s]
40% 14/35 [00:12<00:18, 1.12it/s]
43% 15/35 [00:13<00:17, 1.11it/s]
46% 16/35 [00:14<00:17, 1.10it/s]
49% 17/35 [00:15<00:16, 1.09it/s]
51% 18/35 [00:15<00:15, 1.10it/s]
54% 19/35 [00:16<00:14, 1.10it/s]
57% 20/35 [00:17<00:13, 1.10it/s]
60% 21/35 [00:18<00:12, 1.11it/s]
63% 22/35 [00:19<00:11, 1.12it/s]
66% 23/35 [00:20<00:10, 1.13it/s]
69% 24/35 [00:21<00:09, 1.14it/s]
71% 25/35 [00:22<00:08, 1.15it/s]
74% 26/35 [00:23<00:07, 1.15it/s]
77% 27/35 [00:23<00:06, 1.16it/s]
80% 28/35 [00:24<00:06, 1.15it/s]
83% 29/35 [00:25<00:05, 1.16it/s]
86% 30/35 [00:26<00:04, 1.14it/s]
89% 31/35 [00:27<00:03, 1.15it/s]
91% 32/35 [00:28<00:02, 1.15it/s]
94% 33/35 [00:29<00:01, 1.15it/s]
97% 34/35 [00:29<00:00, 1.16it/s]
100% 35/35 [00:30<00:00, 1.15it/s]
Note: The LoRa's I have loaded were not even registered within the Notebook, leaving no effect towards the diffusion except almost immediately disconnect the notebook due to me trying to put the LoRa's in effect.
Error while deserializing header: MetadataIncompleteBuffer
What LoRAs are you using? I assume that you are downloading it via Batchlinks? I tested it with my favorite LoRAs, and all of which works, probably a problem on your downloaded LoRAs.
About the 10 minutes, yeah I experience it too for some reason. This is probably Colab's way of limiting usage, I have no control over this.
LoRA's: lora:Rabbit (wlsdnjs950):0.8, lora:aki:0.3, lora:3DMM_V11:0.5, lora:add_detail:0.6
These are the LoRA's I would use in order to diffuse different pieces of media. Yet, maybe around 2 minutes of implementing them into the system, it would give me the error below. 👇
"loading Lora /content/stable-diffusion-webui/models/Lora/3DMM_V11.safetensors: SafetensorError
Traceback (most recent call last):
File "/content/stable-diffusion-webui/extensions-builtin/Lora/lora.py", line 253, in load_loras
lora = load_lora(name, lora_on_disk)
File "/content/stable-diffusion-webui/extensions-builtin/Lora/lora.py", line 162, in load_lora
sd = sd_models.read_state_dict(lora_on_disk.filename)
File "/content/stable-diffusion-webui/modules/sd_models.py", line 250, in read_state_dict
pl_sd = safetensors.torch.load_file(checkpoint_file, device=device)
File "/usr/local/lib/python3.10/dist-packages/safetensors/torch.py", line 259, in load_file
with safe_open(filename, framework="pt", device=device) as f:
safetensors_rust.SafetensorError: Error while deserializing header: MetadataIncompleteBuffer"
But that's the thing, it doesn't screw up until I add the LoRA's, but if I just use the model as is, no problems occur.