What happened and why was it ungood?
Python 3.13.12 (tags/v3.13.12:1cbe481, Feb 3 2026, 18:22:25) [MSC v.1944 64 bit (AMD64)]
Version: neo
*** Error running install.py for extension D:\Stable diffusion\forge-neo\extensions\sd-forge-deforum.
*** Command: "D:\Stable diffusion\forge-neo\venv\Scripts\python.exe" "D:\Stable diffusion\forge-neo\extensions\sd-forge-deforum\install.py"
*** Error code: 1
*** stdout: [Deforum] Running on Forge Neo - skipping compatibility patches
*** Deforum: Running on Forge Neo - skipping dependency upgrades (using Neo's versions)
*** Installing Deforum requirement: sentencepiece>=0.1.99 # Required by T5Tokenizer (LTX-2)
*** stderr: Traceback (most recent call last):
*** File "D:\Stable diffusion\forge-neo\extensions\sd-forge-deforum\install.py", line 160, in
*** launch.run_pip(f"install {lib}", f"Deforum requirement: {lib}")
*** ~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
*** File "D:\Stable diffusion\forge-neo\modules\launch_utils.py", line 131, in run_pip
*** return run(f'"{python}" -m pip {command} --prefer-binary{index_url_line}', desc=f"Installing {desc}", errdesc=f"Couldn't install {desc}", live=live)
*** File "D:\Stable diffusion\forge-neo\modules\launch_utils.py", line 86, in run
*** raise RuntimeError("\n".join(error_bits))
*** RuntimeError: Couldn't install Deforum requirement: sentencepiece>=0.1.99 # Required by T5Tokenizer (LTX-2).
*** Command: "D:\Stable diffusion\forge-neo\venv\Scripts\python.exe" -m pip install sentencepiece>=0.1.99 # Required by T5Tokenizer (LTX-2) --prefer-binary
*** Error code: 1
*** stderr: ERROR: Invalid requirement: '#': Expected package name at the start of dependency specifier
*** #
*** ^
Launching Web UI with arguments:
Total VRAM 8151 MB, total RAM 14719 MB memory_management.py :: INFO
PyTorch Version: 2.11.0+cu130 memory_management.py :: INFO
VRAM State: NORMAL_VRAM memory_management.py :: INFO
Device: NVIDIA GeForce RTX 5060 Laptop GPU (cuda:0) - native memory_management.py :: INFO
Hint: your device supports --cuda-malloc for potential speed improvements memory_management.py :: WARNING
Clearing Python bytecode cache...
✓ Cache cleared
[Deforum] Running on Forge Neo - skipping compatibility patches
◤ ◥
▓▓▒▒░░ ⚡ Zirteq's Fluxabled Fork of the Deforum Extension for Forge Neo Fork of Forge WebUI Fork of Automatic1111 ⚡ ░░▒▒▓▓
RECOMMENDED: Dedicated/Isolated Forge Neo Instance
Why: Hijacks Forge output pipeline (custom dashboard, progress bars, suppressed logs)
Patches sigma timesteps for continuous 1% strength resolution (vs 5% at 20 steps)
May conflict with other extensions - optimized specifically for Deforum workflows
Forge Neo: https://github.com/Haoming02/sd-webui-forge-classic/tree/neo
This Fork: https://github.com/Tok/sd-forge-deforum (commit: Unknown)
Primary Target: Forge Neo (fully tested and supported)
Other Forge Versions: May work but remain untested
◣ ◢
Using PyTorch Cross Attention attention.py :: INFO
Using PyTorch Attention for VAE attention.py :: INFO
ControlNet preprocessor location: D:\Stable diffusion\forge-neo\models\ControlNetPreprocessor
INFO: Applying compatibility patches: RMSNorm, FlowMatch, SDPA, Flux ControlNet, KModel
INFO: FlowMatchEulerDiscreteScheduler.time_shift patched
INFO: ✓ Forge Neo has native Flux ControlNet support - no patching needed
INFO: KModel.apply_model patched (ControlNet sample injection)
INFO: Applied fractional img2img patch - 1% strength precision enabled
INFO: Applied fractional sigma slicer patch - fractional t_enc now supported
======================================================================
⚠️ Deforum Model Setup Required
📦 Flux models NOT installed (~15GB download required)
Required for: Flux render modes
📦 Wan FLF2V model NOT installed (~14GB download required)
Required for: Flux + Interpolation mode with Wan FLF2V
✅ Models are OPTIONAL - only download what you need:
• Z-Image, Lumina, SDXL: Work without Flux/Wan
• Qwen: Auto-downloads when you click 'Enhance Prompts'
📥 To download models:
• Automatic: ./shell_scripts/download-all-models.sh
• Manual: Wan Models tab → Download buttons
💡 Tip: You can use Deforum now with Z-Image, Lumina, or SDXL!
*** Error loading script: deforum.py
Traceback (most recent call last):
File "D:\Stable diffusion\forge-neo\modules\scripts.py", line 530, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
File "D:\Stable diffusion\forge-neo\modules\script_loading.py", line 13, in load_module
module_spec.loader.exec_module(module)
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^
File "", line 1023, in exec_module
File "", line 488, in call_with_frames_removed
File "D:\Stable diffusion\forge-neo\extensions\sd-forge-deforum\scripts\deforum.py", line 116, in
init_deforum()
~~~~~~~~~~~~^^
File "D:\Stable diffusion\forge-neo\extensions\sd-forge-deforum\scripts\deforum.py", line 97, in init_deforum
from deforum.ui.ui_right import on_ui_tabs
File "D:\Stable diffusion\forge-neo\extensions\sd-forge-deforum\deforum\ui_init.py", line 3, in
from .ui_right import on_ui_tabs
File "D:\Stable diffusion\forge-neo\extensions\sd-forge-deforum\deforum\ui\ui_right.py", line 23, in
from deforum.orchestration.run_deforum import run_deforum
File "D:\Stable diffusion\forge-neo\extensions\sd-forge-deforum\deforum\orchestration_init_.py", line 4, in
from .render import render_animation
File "D:\Stable diffusion\forge-neo\extensions\sd-forge-deforum\deforum\orchestration\render.py", line 48, in
from modules import devices, sd_hijack
ImportError: cannot import name 'sd_hijack' from 'modules' (unknown location)
ControlNet UI callback registered. controlnet_ui_group.py :: INFO
loading settings: JSONDecodeError
Traceback (most recent call last):
File "D:\Stable diffusion\forge-neo\modules\ui_loadsave.py", line 30, in init
self.ui_settings = self.read_from_file()
~~~~~~~~~~~~~~~~~~~^^
File "D:\Stable diffusion\forge-neo\modules\ui_loadsave.py", line 160, in read_from_file
return json.load(file)
~~~~~~~~~^^^^^^
File "C:\Users\mrbla\AppData\Local\Programs\Python\Python313\Lib\json_init_.py", line 298, in load
return loads(fp.read(),
cls=cls, object_hook=object_hook,
parse_float=parse_float, parse_int=parse_int,
parse_constant=parse_constant, object_pairs_hook=object_pairs_hook, **kw)
File "C:\Users\mrbla\AppData\Local\Programs\Python\Python313\Lib\json_init_.py", line 352, in loads
return _default_decoder.decode(s)
~~~~~~~~~~~~~~~~~~~~~~~^^^
File "C:\Users\mrbla\AppData\Local\Programs\Python\Python313\Lib\json\decoder.py", line 345, in decode
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\mrbla\AppData\Local\Programs\Python\Python313\Lib\json\decoder.py", line 363, in raw_decode
raise JSONDecodeError("Expecting value", s, err.value) from None
json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)
Model Selected: main_entry.py :: INFO
{
"checkpoint": "juggernautXL_ragnarokBy.safetensors",
"modules": [],
"dtype": "[torch.float16, torch.bfloat16]"
}
Patch LoRAs on-the-fly: False main_entry.py :: INFO
Running on local URL: http://127.0.0.1:7860
To create a public link, set share=True in launch().
Startup time: 24.5s (prepare environment: 4.3s, launcher: 0.6s, forge init: 7.6s, shared init: 0.4s, misc. imports: 5.9s, load scripts: 1.8s, create ui: 3.0s, gradio launch: 1.0s).
What happened and why was it ungood?
Python 3.13.12 (tags/v3.13.12:1cbe481, Feb 3 2026, 18:22:25) [MSC v.1944 64 bit (AMD64)]
Version: neo
*** Error running install.py for extension D:\Stable diffusion\forge-neo\extensions\sd-forge-deforum.
*** Command: "D:\Stable diffusion\forge-neo\venv\Scripts\python.exe" "D:\Stable diffusion\forge-neo\extensions\sd-forge-deforum\install.py"
*** Error code: 1
*** stdout: [Deforum] Running on Forge Neo - skipping compatibility patches
*** Deforum: Running on Forge Neo - skipping dependency upgrades (using Neo's versions)
*** Installing Deforum requirement: sentencepiece>=0.1.99 # Required by T5Tokenizer (LTX-2)
*** stderr: Traceback (most recent call last):
*** File "D:\Stable diffusion\forge-neo\extensions\sd-forge-deforum\install.py", line 160, in
*** launch.run_pip(f"install {lib}", f"Deforum requirement: {lib}")
*** ~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
*** File "D:\Stable diffusion\forge-neo\modules\launch_utils.py", line 131, in run_pip
*** return run(f'"{python}" -m pip {command} --prefer-binary{index_url_line}', desc=f"Installing {desc}", errdesc=f"Couldn't install {desc}", live=live)
*** File "D:\Stable diffusion\forge-neo\modules\launch_utils.py", line 86, in run
*** raise RuntimeError("\n".join(error_bits))
*** RuntimeError: Couldn't install Deforum requirement: sentencepiece>=0.1.99 # Required by T5Tokenizer (LTX-2).
*** Command: "D:\Stable diffusion\forge-neo\venv\Scripts\python.exe" -m pip install sentencepiece>=0.1.99 # Required by T5Tokenizer (LTX-2) --prefer-binary
*** Error code: 1
*** stderr: ERROR: Invalid requirement: '#': Expected package name at the start of dependency specifier
*** #
*** ^
Launching Web UI with arguments:
Total VRAM 8151 MB, total RAM 14719 MB memory_management.py :: INFO
PyTorch Version: 2.11.0+cu130 memory_management.py :: INFO
VRAM State: NORMAL_VRAM memory_management.py :: INFO
Device: NVIDIA GeForce RTX 5060 Laptop GPU (cuda:0) - native memory_management.py :: INFO
Hint: your device supports --cuda-malloc for potential speed improvements memory_management.py :: WARNING
Clearing Python bytecode cache...
✓ Cache cleared
[Deforum] Running on Forge Neo - skipping compatibility patches
◤ ◥
▓▓▒▒░░ ⚡ Zirteq's Fluxabled Fork of the Deforum Extension for Forge Neo Fork of Forge WebUI Fork of Automatic1111 ⚡ ░░▒▒▓▓
RECOMMENDED: Dedicated/Isolated Forge Neo Instance
Why: Hijacks Forge output pipeline (custom dashboard, progress bars, suppressed logs)
Patches sigma timesteps for continuous 1% strength resolution (vs 5% at 20 steps)
May conflict with other extensions - optimized specifically for Deforum workflows
Forge Neo: https://github.com/Haoming02/sd-webui-forge-classic/tree/neo
This Fork: https://github.com/Tok/sd-forge-deforum (commit: Unknown)
Primary Target: Forge Neo (fully tested and supported)
Other Forge Versions: May work but remain untested
◣ ◢
Using PyTorch Cross Attention attention.py :: INFO
Using PyTorch Attention for VAE attention.py :: INFO
ControlNet preprocessor location: D:\Stable diffusion\forge-neo\models\ControlNetPreprocessor
INFO: Applying compatibility patches: RMSNorm, FlowMatch, SDPA, Flux ControlNet, KModel
INFO: FlowMatchEulerDiscreteScheduler.time_shift patched
INFO: ✓ Forge Neo has native Flux ControlNet support - no patching needed
INFO: KModel.apply_model patched (ControlNet sample injection)
INFO: Applied fractional img2img patch - 1% strength precision enabled
INFO: Applied fractional sigma slicer patch - fractional t_enc now supported
======================================================================
⚠️ Deforum Model Setup Required
📦 Flux models NOT installed (~15GB download required)
Required for: Flux render modes
📦 Wan FLF2V model NOT installed (~14GB download required)
Required for: Flux + Interpolation mode with Wan FLF2V
✅ Models are OPTIONAL - only download what you need:
• Z-Image, Lumina, SDXL: Work without Flux/Wan
• Qwen: Auto-downloads when you click 'Enhance Prompts'
📥 To download models:
• Automatic: ./shell_scripts/download-all-models.sh
• Manual: Wan Models tab → Download buttons
💡 Tip: You can use Deforum now with Z-Image, Lumina, or SDXL!
*** Error loading script: deforum.py
Traceback (most recent call last):
File "D:\Stable diffusion\forge-neo\modules\scripts.py", line 530, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
File "D:\Stable diffusion\forge-neo\modules\script_loading.py", line 13, in load_module
module_spec.loader.exec_module(module)
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^
File "", line 1023, in exec_module
File "", line 488, in call_with_frames_removed
File "D:\Stable diffusion\forge-neo\extensions\sd-forge-deforum\scripts\deforum.py", line 116, in
init_deforum()
~~~~~~~~~~~~^^
File "D:\Stable diffusion\forge-neo\extensions\sd-forge-deforum\scripts\deforum.py", line 97, in init_deforum
from deforum.ui.ui_right import on_ui_tabs
File "D:\Stable diffusion\forge-neo\extensions\sd-forge-deforum\deforum\ui_init.py", line 3, in
from .ui_right import on_ui_tabs
File "D:\Stable diffusion\forge-neo\extensions\sd-forge-deforum\deforum\ui\ui_right.py", line 23, in
from deforum.orchestration.run_deforum import run_deforum
File "D:\Stable diffusion\forge-neo\extensions\sd-forge-deforum\deforum\orchestration_init_.py", line 4, in
from .render import render_animation
File "D:\Stable diffusion\forge-neo\extensions\sd-forge-deforum\deforum\orchestration\render.py", line 48, in
from modules import devices, sd_hijack
ImportError: cannot import name 'sd_hijack' from 'modules' (unknown location)
ControlNet UI callback registered. controlnet_ui_group.py :: INFO
loading settings: JSONDecodeError
Traceback (most recent call last):
File "D:\Stable diffusion\forge-neo\modules\ui_loadsave.py", line 30, in init
self.ui_settings = self.read_from_file()
~~~~~~~~~~~~~~~~~~~^^
File "D:\Stable diffusion\forge-neo\modules\ui_loadsave.py", line 160, in read_from_file
return json.load(file)
~~~~~~~~~^^^^^^
File "C:\Users\mrbla\AppData\Local\Programs\Python\Python313\Lib\json_init_.py", line 298, in load
return loads(fp.read(),
cls=cls, object_hook=object_hook,
parse_float=parse_float, parse_int=parse_int,
parse_constant=parse_constant, object_pairs_hook=object_pairs_hook, **kw)
File "C:\Users\mrbla\AppData\Local\Programs\Python\Python313\Lib\json_init_.py", line 352, in loads
return _default_decoder.decode(s)
~~~~~~~~~~~~~~~~~~~~~~~^^^
File "C:\Users\mrbla\AppData\Local\Programs\Python\Python313\Lib\json\decoder.py", line 345, in decode
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\mrbla\AppData\Local\Programs\Python\Python313\Lib\json\decoder.py", line 363, in raw_decode
raise JSONDecodeError("Expecting value", s, err.value) from None
json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)
Model Selected: main_entry.py :: INFO
{
"checkpoint": "juggernautXL_ragnarokBy.safetensors",
"modules": [],
"dtype": "[torch.float16, torch.bfloat16]"
}
Patch LoRAs on-the-fly: False main_entry.py :: INFO
Running on local URL: http://127.0.0.1:7860
To create a public link, set
share=Trueinlaunch().Startup time: 24.5s (prepare environment: 4.3s, launcher: 0.6s, forge init: 7.6s, shared init: 0.4s, misc. imports: 5.9s, load scripts: 1.8s, create ui: 3.0s, gradio launch: 1.0s).