search

deforum-art / sd-webui-deforum

Deforum extension for AUTOMATIC1111's Stable Diffusion webui
https://deforum.github.io
Other
2.7k stars 390 forks source link

[Bug]: Upscale not working on Linux Cloudserver (RunDiffusion) #744

Open revolvedai opened 1 year ago

revolvedai commented 1 year ago

Have you read the latest version of the FAQ?

Is there an existing issue for this?

Are you using the latest version of the Deforum extension?

What happened?

Upscaling is not working while using Deforum on a Linux server in the cloud

Steps to reproduce the problem

  1. Click upscale in Output tab
  2. Click Generate

What should have happened?

Deforum video generates and then upscales

WebUI and Deforum extension Commit IDs

Webui Commit - 89f9faa63388756314e8a1d96cf86bf5e0663045 deforum exten commit id - 0ed7c4c847d1a62e8ad46c36edd0adee5440402d

Torch version

torch version 2.0.0+cu118 installed.

On which platform are you launching the webui with the extension?

Cloud server (Linux)

Deforum settings

https://gist.github.com/rundiffusion/cdc09eb426519c7537d3de9b804f6c81

Webui core settings

https://gist.github.com/rundiffusion/65c8d84f9dc8b906bfb0837aa816b261

Console logs

https://gist.github.com/rundiffusion/69f57fbee36ff1003d4deb422060d33d

################################################################
Install script for stable-diffusion + Web UI
Tested on Debian 11 (Bullseye)
################################################################

################################################################
Running on workspace user
################################################################

################################################################
Repo already cloned, using it as install directory
################################################################

################################################################
Create and activate python venv
################################################################

################################################################
Launching launch.py...
################################################################
Using TCMalloc: libtcmalloc.so.4
Python 3.10.6 (main, Nov 14 2022, 16:10:14) [GCC 11.3.0]
Version: v1.2.1
Commit hash: 89f9faa63388756314e8a1d96cf86bf5e0663045
Installing requirements

Installing sd-dynamic-prompts requirements.txt

No module 'xformers'. Proceeding without it.
If submitting an issue on github, please provide the full startup log for debugging purposes.

Initializing Dreambooth
Dreambooth revision: 926ae204ef5de17efca2059c334b6098492a0641
Successfully installed fastapi-0.94.1 gitpython-3.1.31 google-auth-oauthlib-0.4.6 transformers-4.26.1

Does your project take forever to startup?
Repetitive dependency installation may be the reason.
Automatic1111's base project sets strict requirements on outdated dependencies.
If an extension is using a newer version, the dependency is uninstalled and reinstalled twice every startup.

[!] xformers NOT installed.
[+] torch version 2.0.0+cu118 installed.
[+] torchvision version 0.15.1+cu118 installed.
[+] accelerate version 0.18.0 installed.
[+] diffusers version 0.14.0 installed.
[+] transformers version 4.26.1 installed.
[+] bitsandbytes version 0.35.4 installed.

Launching Web UI with arguments: --listen --enable-insecure-extension-access
2023-05-24 03:58:55.356217: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
2023-05-24 03:58:56.030006: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
No module 'xformers'. Proceeding without it.
Additional Network extension not installed, Only hijack built-in lora
LoCon Extension hijack built-in lora successfully
ControlNet v1.1.179
ControlNet v1.1.179
Loading weights [6ce0161689] from /home/workspace/stable-diffusion-webui/models/Stable-diffusion/v1-5-pruned-emaonly.safetensors
Creating model from config: /home/workspace/stable-diffusion-webui/configs/v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Applying cross attention optimization (Doggettx).
Textual inversion embeddings loaded(0):
Model loaded in 2.4s (load weights from disk: 0.1s, create model: 0.6s, apply weights to model: 0.8s, apply half(): 0.4s, move model to device: 0.5s).
*Deforum ControlNet support: enabled*
Running on local URL:  http://0.0.0.0:7860

To create a public link, set `share=True` in `launch()`.
Startup time: 10.8s (import torch: 2.7s, import gradio: 1.2s, import ldm: 0.3s, other imports: 0.8s, load scripts: 4.8s, create ui: 0.8s, gradio launch: 0.1s).
Deforum extension for auto1111 webui, v2.4b
Git commit: 0ed7c4c8 (Tue May 23 10:01:06 2023)
Saving animation frames to:
/home/workspace/stable-diffusion-webui/outputs/img2img-images/Deforum_20230524041807
Animation frame: 0/25
Seed: 3982779079
Prompt: tiny cute swamp bunny, highly detailed, intricate, ultra hd, sharp photo, crepuscular rays, in focus, by tomasz alen kopera
Neg Prompt: nsfw, nude
Not using an init image (doing pure txt2img)
╭─────┬───┬───────┬─────┬──────┬────┬────╮
│Steps│CFG│Denoise│Angle│ Zoom │Tr X│Tr Y│
├─────┼───┼───────┼─────┼──────┼────┼────┤
│ 25  │7.0│   0   │  0  │1.0025│ 0  │ 0  │
╰─────┴───┴───────┴─────┴──────┴────┴────╯
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 25/25 [00:03<00:00,  7.25it/s]
Animation frame: 2/25  ███████████████████████▊                                                                                                       | 25/133 [00:02<00:11,  9.73it/s]
Creating in-between cadence frame: 0; tween:0.50;
Creating in-between cadence frame: 1; tween:1.00;
Seed: 3982779080
Prompt: tiny cute swamp bunny, highly detailed, intricate, ultra hd, sharp photo, crepuscular rays, in focus, by tomasz alen kopera
Neg Prompt: nsfw, nude
╭─────┬───┬───────┬─────┬─────┬────┬────╮
│Steps│CFG│Denoise│Angle│Zoom │Tr X│Tr Y│
├─────┼───┼───────┼─────┼─────┼────┼────┤
│ 25  │7.0│ 0.35  │  0  │1.003│ 0  │ 0  │
╰─────┴───┴───────┴─────┴─────┴────┴────╯
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:00<00:00, 10.07it/s]
Animation frame: 4/25  ████████████████████████████████▍                                                                                              | 34/133 [00:05<00:16,  6.01it/s]
Creating in-between cadence frame: 2; tween:0.50;
Creating in-between cadence frame: 3; tween:1.00;
Seed: 3982779081
Prompt: tiny cute swamp bunny, highly detailed, intricate, ultra hd, sharp photo, crepuscular rays, in focus, by tomasz alen kopera
Neg Prompt: nsfw, nude
╭─────┬───┬───────┬─────┬──────┬────┬────╮
│Steps│CFG│Denoise│Angle│ Zoom │Tr X│Tr Y│
├─────┼───┼───────┼─────┼──────┼────┼────┤
│ 25  │7.0│ 0.35  │  0  │1.0035│ 0  │ 0  │
╰─────┴───┴───────┴─────┴──────┴────┴────╯
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:00<00:00, 10.08it/s]
Animation frame: 6/25  █████████████████████████████████████████                                                                                      | 43/133 [00:06<00:11,  7.81it/s]
Creating in-between cadence frame: 4; tween:0.50;
Creating in-between cadence frame: 5; tween:1.00;
Seed: 3982779082
Prompt: tiny cute swamp bunny, highly detailed, intricate, ultra hd, sharp photo, crepuscular rays, in focus, by tomasz alen kopera
Neg Prompt: nsfw, nude
╭─────┬───┬───────┬─────┬──────┬────┬────╮
│Steps│CFG│Denoise│Angle│ Zoom │Tr X│Tr Y│
├─────┼───┼───────┼─────┼──────┼────┼────┤
│ 25  │7.0│ 0.35  │  0  │1.0039│ 0  │ 0  │
╰─────┴───┴───────┴─────┴──────┴────┴────╯
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:00<00:00, 10.03it/s]
Animation frame: 8/25  █████████████████████████████████████████████████▋                                                                             | 52/133 [00:07<00:09,  8.40it/s]
Creating in-between cadence frame: 6; tween:0.50;
Creating in-between cadence frame: 7; tween:1.00;
Seed: 3982779083
Prompt: tiny cute swamp bunny, highly detailed, intricate, ultra hd, sharp photo, crepuscular rays, in focus, by tomasz alen kopera
Neg Prompt: nsfw, nude
╭─────┬───┬───────┬─────┬──────┬────┬────╮
│Steps│CFG│Denoise│Angle│ Zoom │Tr X│Tr Y│
├─────┼───┼───────┼─────┼──────┼────┼────┤
│ 25  │7.0│ 0.35  │  0  │1.0042│ 0  │ 0  │
╰─────┴───┴───────┴─────┴──────┴────┴────╯
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:00<00:00, 10.02it/s]
Animation frame: 10/25  █████████████████████████████████████████████████████████▏                                                                    | 61/133 [00:09<00:08,  8.21it/s]
Creating in-between cadence frame: 8; tween:0.50;
Creating in-between cadence frame: 9; tween:1.00;
Seed: 3982779084
Prompt: tiny cute swamp bunny, highly detailed, intricate, ultra hd, sharp photo, crepuscular rays, in focus, by tomasz alen kopera
Neg Prompt: nsfw, nude
╭─────┬───┬───────┬─────┬──────┬────┬────╮
│Steps│CFG│Denoise│Angle│ Zoom │Tr X│Tr Y│
├─────┼───┼───────┼─────┼──────┼────┼────┤
│ 25  │7.0│ 0.35  │  0  │1.0044│ 0  │ 0  │
╰─────┴───┴───────┴─────┴──────┴────┴────╯
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:00<00:00, 10.02it/s]
Animation frame: 12/25  █████████████████████████████████████████████████████████████████▊                                                            | 70/133 [00:10<00:07,  8.33it/s]
Creating in-between cadence frame: 10; tween:0.50;
Creating in-between cadence frame: 11; tween:1.00;
Seed: 3982779085
Prompt: tiny cute swamp bunny, highly detailed, intricate, ultra hd, sharp photo, crepuscular rays, in focus, by tomasz alen kopera
Neg Prompt: nsfw, nude
╭─────┬───┬───────┬─────┬──────┬────┬────╮
│Steps│CFG│Denoise│Angle│ Zoom │Tr X│Tr Y│
├─────┼───┼───────┼─────┼──────┼────┼────┤
│ 25  │7.0│ 0.35  │  0  │1.0045│ 0  │ 0  │
╰─────┴───┴───────┴─────┴──────┴────┴────╯
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:00<00:00, 10.00it/s]
Animation frame: 14/25  ██████████████████████████████████████████████████████████████████████████▍                                                   | 79/133 [00:11<00:06,  8.59it/s]
Creating in-between cadence frame: 12; tween:0.50;
Creating in-between cadence frame: 13; tween:1.00;
Seed: 3982779086
Prompt: tiny cute swamp bunny, highly detailed, intricate, ultra hd, sharp photo, crepuscular rays, in focus, by tomasz alen kopera
Neg Prompt: nsfw, nude
╭─────┬───┬───────┬─────┬──────┬────┬────╮
│Steps│CFG│Denoise│Angle│ Zoom │Tr X│Tr Y│
├─────┼───┼───────┼─────┼──────┼────┼────┤
│ 25  │7.0│ 0.35  │  0  │1.0044│ 0  │ 0  │
╰─────┴───┴───────┴─────┴──────┴────┴────╯
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:00<00:00,  9.98it/s]
Animation frame: 16/25  ███████████████████████████████████████████████████████████████████████████████████                                           | 88/133 [00:13<00:05,  8.66it/s]
Creating in-between cadence frame: 14; tween:0.50;
Creating in-between cadence frame: 15; tween:1.00;
Seed: 3982779087
Prompt: tiny cute swamp bunny, highly detailed, intricate, ultra hd, sharp photo, crepuscular rays, in focus, by tomasz alen kopera
Neg Prompt: nsfw, nude
╭─────┬───┬───────┬─────┬──────┬────┬────╮
│Steps│CFG│Denoise│Angle│ Zoom │Tr X│Tr Y│
├─────┼───┼───────┼─────┼──────┼────┼────┤
│ 25  │7.0│ 0.35  │  0  │1.0042│ 0  │ 0  │
╰─────┴───┴───────┴─────┴──────┴────┴────╯
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:00<00:00, 10.00it/s]
Animation frame: 18/25  ███████████████████████████████████████████████████████████████████████████████████████████▌                                  | 97/133 [00:14<00:04,  8.38it/s]
Creating in-between cadence frame: 16; tween:0.50;
Creating in-between cadence frame: 17; tween:1.00;
Seed: 3982779088
Prompt: tiny cute swamp bunny, highly detailed, intricate, ultra hd, sharp photo, crepuscular rays, in focus, by tomasz alen kopera
Neg Prompt: nsfw, nude
╭─────┬───┬───────┬─────┬──────┬────┬────╮
│Steps│CFG│Denoise│Angle│ Zoom │Tr X│Tr Y│
├─────┼───┼───────┼─────┼──────┼────┼────┤
│ 25  │7.0│ 0.35  │  0  │1.0039│ 0  │ 0  │
╰─────┴───┴───────┴─────┴──────┴────┴────╯
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:00<00:00, 10.01it/s]
Animation frame: 20/25  ███████████████████████████████████████████████████████████████████████████████████████████████████▍                         | 106/133 [00:16<00:03,  8.35it/s]
Creating in-between cadence frame: 18; tween:0.50;
Creating in-between cadence frame: 19; tween:1.00;
Seed: 3982779089
Prompt: tiny cute swamp bunny, highly detailed, intricate, ultra hd, sharp photo, crepuscular rays, in focus, by tomasz alen kopera
Neg Prompt: nsfw, nude
╭─────┬───┬───────┬─────┬──────┬────┬────╮
│Steps│CFG│Denoise│Angle│ Zoom │Tr X│Tr Y│
├─────┼───┼───────┼─────┼──────┼────┼────┤
│ 25  │7.0│ 0.35  │  0  │1.0035│ 0  │ 0  │
╰─────┴───┴───────┴─────┴──────┴────┴────╯
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:00<00:00, 10.00it/s]
Animation frame: 22/25  ███████████████████████████████████████████████████████████████████████████████████████████████████████████▉                 | 115/133 [00:17<00:02,  8.64it/s]
Creating in-between cadence frame: 20; tween:0.50;
Creating in-between cadence frame: 21; tween:1.00;
Seed: 3982779090
Prompt: tiny cute swamp bunny, highly detailed, intricate, ultra hd, sharp photo, crepuscular rays, in focus, by tomasz alen kopera
Neg Prompt: nsfw, nude
╭─────┬───┬───────┬─────┬─────┬────┬────╮
│Steps│CFG│Denoise│Angle│Zoom │Tr X│Tr Y│
├─────┼───┼───────┼─────┼─────┼────┼────┤
│ 25  │7.0│ 0.35  │  0  │1.003│ 0  │ 0  │
╰─────┴───┴───────┴─────┴─────┴────┴────╯
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:00<00:00,  9.98it/s]
Animation frame: 24/25  ███████████████████████████████████████████████████████████████████████████████████████████████████████████████████▌         | 123/133 [00:18<00:01,  8.84it/s]
Creating in-between cadence frame: 22; tween:0.50;
Creating in-between cadence frame: 23; tween:1.00;
Seed: 3982779091
Prompt: tiny cute swamp bunny, highly detailed, intricate, ultra hd, sharp photo, crepuscular rays, in focus, by tomasz alen kopera
Neg Prompt: nsfw, nude
╭─────┬───┬───────┬─────┬──────┬────┬────╮
│Steps│CFG│Denoise│Angle│ Zoom │Tr X│Tr Y│
├─────┼───┼───────┼─────┼──────┼────┼────┤
│ 25  │7.0│ 0.35  │  0  │1.0025│ 0  │ 0  │
╰─────┴───┴───────┴─────┴──────┴────┴────╯
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:00<00:00, 10.00it/s]
Deforum progress: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 133/133 [00:20<00:00,  6.51it/s]
Got a request to stitch frames to video using FFmpeg.
Frames:
/home/workspace/stable-diffusion-webui/outputs/img2img-images/Deforum_20230524041807/20230524041807_%09d.png
To Video:
/home/workspace/stable-diffusion-webui/outputs/img2img-images/Deforum_20230524041807/20230524041807.mp4
Stitching *video*...
Video stitching done in 0.52 seconds!
Upscaling raw output PNGs using realesr-animevideov3 at 2x...Error completing request
Arguments: ('task(v40d34li6sdui50)', None, False, None, '2D', 25, 'replicate', '0: (0)', '0: (1.0025+0.002*sin(1.25*3.14*t/30))', '0: (0)', '0: (0)', '0: (1.75)', '0: (0.5)', '0: (0.5)', '0: (0)', '0: (0)', '0: (0)', False, '0: (0)', '0: (0)', '0: (0)', '0: (53)', '0: (0.065)', '0: (0.65)', '0: (1.0)', '0: (7)', False, '0: (25)', '0: (70)', '0: (1)', False, '0: (200)', '0: (10000)', '0:(s), 1:(-1), "max_f-2":(-1), "max_f-1":(s)', '0:(1.5)', False, '0: (1)', '0: (0)', False, '0: ("Euler a")', False, '0: ("{video_mask}")', '0: ("{video_mask}")', False, '0: ("model1.ckpt"), 100: ("model2.safetensors")', False, '0: (2)', True, '0: (1.05)', False, '20230129210106', False, '0: (0)', False, '0: (1)', '0: (0.1)', '0: (5)', '0: (1)', '0: (0)', 'LAB', '', 1, False, False, 2, 'None', '0: (1)', 'None', '0: (1)', '0', 'perlin', 8, 8, 4, 0.5, True, 'Midas-3-Hybrid', 0.2, 'border', 'bicubic', False, 'https://deforum.github.io/a1/V1.mp4', 1, 0, -1, False, False, 'https://deforum.github.io/a1/VM1.mp4', '0:(0.5)', '0:(0.5)', '0:(1)', '0:(100)', '0:(0)', '0:(1)', False, 'None', True, 'None', False, False, 2, 'RAFT', 'None', False, 'None', False, 'None', False, False, '{\n    "0": "tiny cute swamp bunny, highly detailed, intricate, ultra hd, sharp photo, crepuscular rays, in focus, by tomasz alen kopera",\n    "30": "anthropomorphic clean cat, surrounded by fractals, epic angle and pose, symmetrical, 3d, depth of field, ruan jia and fenghua zhong",\n    "60": "a beautiful coconut --neg photo, realistic",\n    "90": "a beautiful durian, trending on Artstation"\n}\n    ', '', 'nsfw, nude', 512, 512, True, False, False, 0, 0, -1, 'Euler a', 25, 'Deforum_{timestring}', 'iter', 1, False, 0.8, True, 'https://deforum.github.io/a1/I1.png', False, False, 'https://deforum.github.io/a1/M1.jpg', False, 1.0, 1.0, True, 4, 'fill', True, 4, 'ignore', 10.0, False, 15, False, False, 'C:/SD/20230124234916_%09d.png', 'None', 'https://deforum.github.io/a1/A1.mp3', True, '2x', 'realesr-animevideov3', True, False, 'None', 2, False, 2, False, '', True, False, '{\n    "0": "https://deforum.github.io/a1/Gi1.png",\n    "max_f/4-5": "https://deforum.github.io/a1/Gi2.png",\n    "max_f/2-10": "https://deforum.github.io/a1/Gi3.png",\n    "3*max_f/4-15": "https://deforum.github.io/a1/Gi4.jpg",\n    "max_f-20": "https://deforum.github.io/a1/Gi1.png"\n}', '0:(0.75)', '0:(0.35)', '0:(0.25)', '0:(20)', '0:(0.075)', True, '', '', False, False, False, 'none', 'None', '0:(1)', '0:(0.0)', '0:(1.0)', 64, 64, 64, 'Inner Fit (Scale to Fit)', 'Balanced', False, True, '', '', False, False, False, 'none', 'None', '0:(1)', '0:(0.0)', '0:(1.0)', 64, 64, 64, 'Inner Fit (Scale to Fit)', 'Balanced', False, True, '', '', False, False, False, 'none', 'None', '0:(1)', '0:(0.0)', '0:(1.0)', 64, 64, 64, 'Inner Fit (Scale to Fit)', 'Balanced', False, True, '', '', False, False, False, 'none', 'None', '0:(1)', '0:(0.0)', '0:(1.0)', 64, 64, 64, 'Inner Fit (Scale to Fit)', 'Balanced', False, True, '', '', False, False, False, 'none', 'None', '0:(1)', '0:(0.0)', '0:(1.0)', 64, 64, 64, 'Inner Fit (Scale to Fit)', 'Balanced', False) {}
Traceback (most recent call last):
  File "/home/workspace/stable-diffusion-webui/modules/call_queue.py", line 57, in f
    res = list(func(*args, **kwargs))
  File "/home/workspace/stable-diffusion-webui/modules/call_queue.py", line 37, in f
    res = func(*args, **kwargs)
  File "/home/workspace/stable-diffusion-webui/extensions/deforum-for-automatic1111-webui/scripts/deforum_helpers/run_deforum.py", line 155, in run_deforum
    make_upscale_v2(upscale_factor = video_args.r_upscale_factor, upscale_model = video_args.r_upscale_model, keep_imgs = video_args.r_upscale_keep_imgs, imgs_raw_path = args.outdir, imgs_batch_id = root.timestring, fps = video_args.fps, deforum_models_path = root.models_path, current_user_os = root.current_user_os, ffmpeg_location=f_location, stitch_from_frame=0, stitch_to_frame=max_video_frames, ffmpeg_crf=f_crf, ffmpeg_preset=f_preset, add_soundtrack = video_args.add_soundtrack ,audio_path=real_audio_track, srt_path=srt_path)
  File "/home/workspace/stable-diffusion-webui/extensions/deforum-for-automatic1111-webui/scripts/deforum_helpers/upscaling.py", line 143, in make_upscale_v2
    process = subprocess.run(cmd, capture_output=True, check=True, text=True, cwd=(os.path.join(deforum_models_path, 'realesrgan_ncnn') if current_user_os == 'Mac' else None))
  File "/usr/lib/python3.10/subprocess.py", line 524, in run
    raise CalledProcessError(retcode, process.args,
subprocess.CalledProcessError: Command '['/home/workspace/stable-diffusion-webui/models/Deforum/realesrgan_ncnn/realesrgan-ncnn-vulkan', '-i', '/home/workspace/stable-diffusion-webui/outputs/img2img-images/Deforum_20230524041807/20230524041807_upscaled/temp_raw_imgs_to_upscale', '-o', '/home/workspace/stable-diffusion-webui/outputs/img2img-images/Deforum_20230524041807/20230524041807_upscaled', '-s', '-1', '-n', 'realesr-animevideov3']' returned non-zero exit status 127.

Traceback (most recent call last):
  File "/home/workspace/stable-diffusion-webui/venv/lib/python3.10/site-packages/gradio/routes.py", line 408, in run_predict
    output = await app.get_blocks().process_api(
  File "/home/workspace/stable-diffusion-webui/venv/lib/python3.10/site-packages/gradio/blocks.py", line 1318, in process_api
    data = self.postprocess_data(fn_index, result["prediction"], state)
  File "/home/workspace/stable-diffusion-webui/venv/lib/python3.10/site-packages/gradio/blocks.py", line 1221, in postprocess_data
    self.validate_outputs(fn_index, predictions)  # type: ignore
  File "/home/workspace/stable-diffusion-webui/venv/lib/python3.10/site-packages/gradio/blocks.py", line 1196, in validate_outputs
    raise ValueError(
ValueError: An event handler (f) didn't receive enough output values (needed: 4, received: 3).
Wanted outputs:
    [gallery, textbox, textbox, html]
Received outputs:
    [None, "", "<div class='error'>CalledProcessError: Command &#x27;[&#x27;/home/workspace/stable-diffusion-webui/models/Deforum/realesrgan_ncnn/realesrgan-ncnn-vulkan&#x27;, &#x27;-i&#x27;, &#x27;/home/workspace/stable-diffusion-webui/outputs/img2img-images/Deforum_20230524041807/20230524041807_upscaled/temp_raw_imgs_to_upscale&#x27;, &#x27;-o&#x27;, &#x27;/home/workspace/stable-diffusion-webui/outputs/img2img-images/Deforum_20230524041807/20230524041807_upscaled&#x27;, &#x27;-s&#x27;, &#x27;-1&#x27;, &#x27;-n&#x27;, &#x27;realesr-animevideov3&#x27;]&#x27; returned non-zero exit status 127.</div><div class='performance'><p class='time'>Time taken: <wbr>22.98s</p><p class='vram'>Torch active/reserved: 11474/11578 MiB, <wbr>Sys VRAM: 11751/16126 MiB (72.87%)</p></div>"]

Additional information

There's no "Reopen" button! Submitted a second issue. @hithereai

hithereai commented 1 year ago

Gotcha, confirmed. Will take a look.

hithereai commented 1 year ago

Please re try

revolvedai commented 1 year ago

We got infinite hang and error 127. But progress, it generates... just doesn't upscale. Terminal log here: https://gist.github.com/rundiffusion/0d16f025bde2be37823ec7250f979cfb

revolvedai commented 1 year ago

Removed all extensions, fresh install, here’s the terminal log: https://gist.github.com/rundiffusion/36ef53ad619ca550e9455c3e9a2c4e48

@hithereai

hithereai commented 1 year ago

image

So, this is the actual error. I'm not sure I can fix it, need to think about that.

yuvraj108c commented 1 year ago

Not working on ubuntu 22:

Got a request to upscale a video using realesr-animevideov3 at x2 Trying to extract frames from video with input FPS of 12.0. Please wait patiently. Extracted 117 frames from video in 1.74 seconds! Upscaling raw PNGs using realesr-animevideov3 at x2...Traceback (most recent call last): File "/home/user/stable-diffusion-webui/venv/lib/python3.10/site-packages/gradio/routes.py", line 422, in run_predict output = await app.get_blocks().process_api( File "/home/user/stable-diffusion-webui/venv/lib/python3.10/site-packages/gradio/blocks.py", line 1323, in process_api result = await self.call_function( File "/home/user/stable-diffusion-webui/venv/lib/python3.10/site-packages/gradio/blocks.py", line 1051, in call_function prediction = await anyio.to_thread.run_sync( File "/home/user/stable-diffusion-webui/venv/lib/python3.10/site-packages/anyio/to_thread.py", line 33, in run_sync return await get_asynclib().run_sync_in_worker_thread( File "/home/user/stable-diffusion-webui/venv/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 877, in run_sync_in_worker_thread return await future File "/home/user/stable-diffusion-webui/venv/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 807, in run result = context.run(func, *args) File "/home/user/stable-diffusion-webui/extensions/sd-webui-deforum/scripts/deforum_helpers/gradio_funcs.py", line 124, in ncnn_upload_vid_to_upscale process_ncnn_upscale_vid_upload_logic(vid_path, in_vid_fps, in_vid_res, out_vid_res, f_models_path, upscale_model, upscale_factor, keep_imgs, f_location, f_crf, f_preset, current_user) File "/home/user/stable-diffusion-webui/extensions/sd-webui-deforum/scripts/deforum_helpers/upscaling.py", line 31, in process_ncnn_upscale_vid_upload_logic process_ncnn_video_upscaling(vid_path, outdir, in_vid_fps, in_vid_res, out_vid_res, models_path, upscale_model, upscale_factor, keep_imgs, f_location, f_crf, f_preset, current_user_os) File "/home/user/stable-diffusion-webui/extensions/sd-webui-deforum/scripts/deforum_helpers/upscaling.py", line 53, in process_ncnn_video_upscaling process = subprocess.run(cmd, capture_output=True, check=True, text=True) File "/usr/lib/python3.10/subprocess.py", line 524, in run raise CalledProcessError(retcode, process.args, subprocess.CalledProcessError: Command '['/home/user/stable-diffusion-webui/models/Deforum/realesrgan_ncnn/realesrgan-ncnn-vulkan', '-i', '/home/user/stable-diffusion-webui/outputs/frame-upscaling/1_3_1/tmp_input_frames', '-o', '/home/user/stable-diffusion-webui/outputs/frame-upscaling/1_3_1/Upscaled_frames', '-s', '2', '-n', 'realesr-animevideov3']' returned non-zero exit status 127.

MadMick96 commented 1 year ago

This issue seems to be present on cloud computing solutions like Runpod too. https://pastebin.com/QU619SpR

DevilsCrypto commented 1 year ago

I encountered the same issue on vlad automatic as well.

pavelxx1 commented 1 year ago

solution on Ubuntu 😁

apt update
apt install libvulkan1
DevilsCrypto commented 1 year ago

solution on Ubuntu 😁

apt update
apt install libvulkan1

I am also using Ubuntu, but libvulkan1 is already installed.

Are you able to upscale video's?

pavelxx1 commented 1 year ago

solution on Ubuntu 😁

apt update
apt install libvulkan1

I am also using Ubuntu, but libvulkan1 is already installed.

Are you able to upscale video's?

yes, all working fine

chaztaps commented 1 year ago

solution on Ubuntu 😁

apt update
apt install libvulkan1

I am also using Ubuntu, but libvulkan1 is already installed. Are you able to upscale video's?

yes, all working fine

Do you need to perform apt update + apt install libvulkan1 then do a fresh install of web-ui? I ask because Deforum upscaling is still throwing up the same error.

chaztaps commented 1 year ago

solution on Ubuntu 😁

apt update
apt install libvulkan1

I am also using Ubuntu, but libvulkan1 is already installed. Are you able to upscale video's?

yes, all working fine

Do you need to perform apt update + apt install libvulkan1 then do a fresh install of web-ui? I ask because Deforum upscaling is still throwing up the same error.

Nope, this also doesn't work.

Limbicnation commented 1 year ago

solution on Ubuntu grin

apt update
apt install libvulkan1

I am also using Ubuntu, but libvulkan1 is already installed. Are you able to upscale video's?

yes, all working fine

Do you need to perform apt update + apt install libvulkan1 then do a fresh install of web-ui? I ask because Deforum upscaling is still throwing up the same error.

Easy fix would be to download the Linux ZIP and extract the contents into ./models/Deforum/. Then chmod +x ./realesrgan-ncnn-vulkan and everything should work beautifully :)

chaztaps commented 1 year ago

solution on Ubuntu grin

apt update
apt install libvulkan1

I am also using Ubuntu, but libvulkan1 is already installed. Are you able to upscale video's?

yes, all working fine

Do you need to perform apt update + apt install libvulkan1 then do a fresh install of web-ui? I ask because Deforum upscaling is still throwing up the same error.

Easy fix would be to download the Linux ZIP and extract the contents into ./models/Deforum/. Then chmod +x ./realesrgan-ncnn-vulkan and everything should work beautifully :)

I'm afraid this still leads to the same problem as quoted throughout this thread. If it's a GPU compatibility issue (as stated by @hithereai ) then there's not much I can do. Thanks for looking into it though.

Limbicnation commented 1 year ago

solution on Ubuntu grin

apt update
apt install libvulkan1

I am also using Ubuntu, but libvulkan1 is already installed. Are you able to upscale video's?

yes, all working fine

Do you need to perform apt update + apt install libvulkan1 then do a fresh install of web-ui? I ask because Deforum upscaling is still throwing up the same error.

Easy fix would be to download the Linux ZIP and extract the contents into ./models/Deforum/. Then chmod +x ./realesrgan-ncnn-vulkan and everything should work beautifully :)

I'm afraid this still leads to the same problem as quoted throughout this thread. If it's a GPU compatibility issue (as stated by @hithereai ) then there's not much I can do. Thanks for looking into it though.

Ok, thank you for the notice. Strangely, I got it to work yesterday on my system, Ubuntu 22.10 with an RTX graphics card.

fiua commented 1 year ago

I have the same problem in liunx

chaztaps commented 1 year ago

I should probably add that I have been using A1111 with Deforum on a LambdaLabs cloud GPU set up (H100)...

eduardonba1 commented 11 months ago

I have the same problem The interpolation works perfectly, but upscale doesnt

frozzway commented 10 months ago

solution on Ubuntu 😁

apt update
apt install libvulkan1

Upscaling has started but using CPU instead of GPU - very slow

yuvraj108c commented 9 months ago

Upscaling has started but using CPU instead of GPU - very slow

same same