Nil pointer (?) in hunyuan.py

[TGMcLean]

A quick survey shows this has happened in the past. Maybe hunyuan.py needs an update?

Loading model to memory(mps): CLIPTextModel
Traceback (most recent call last):
  File "/.../core_framepackstudio/appstudio.py", line 1109, in worker
    llama_vec, llama_attention_mask, clip_l_pooler = get_cached_or_encode_prompt(
                                                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/.../core_framepackstudio/venv/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 120, in decorate_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/.../core_framepackstudio/appstudio.py", line 977, in get_cached_or_encode_prompt
    llama_vec, clip_l_pooler = encode_prompt_conds(
                               ^^^^^^^^^^^^^^^^^^^^
  File "/.../core_framepackstudio/venv/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 120, in decorate_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/.../core_framepackstudio/diffusers_helper/hunyuan.py", line 39, in encode_prompt_conds
    llama_vec = llama_outputs.hidden_states[-3][:, crop_start:llama_attention_length]
                ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^
TypeError: 'NoneType' object is not subscriptable
...

[loscrossos]

please post the information required in the issue form. that way i csnt support efficiently

[djtrance]

i have exactly the same problem

[TGMcLean]

I'll try and get back to you in the next few days with a proper response.

[Talpik]

llama_outputs=BaseModelOutputWithPast(last_hidden_state=tensor([[[ 1.3330, 0.0251, -0.3379, ..., -0.2549, 0.4644, 0.4375], [-2.0977, -0.8267, 0.7847, ..., -0.4946, 0.3025, 0.0775], [ 1.2969, -1.9561, -0.0808, ..., 2.4863, -0.7622, -1.2021], ..., [-1.5850, -0.9834, 0.6348, ..., -0.5083, 0.3000, -0.7441], [-1.5996, -0.9604, 0.6372, ..., -0.4927, 0.2878, -0.7212], [-1.6240, -0.9517, 0.6045, ..., -0.4568, 0.2830, -0.7061]]], device='mps:0', dtype=torch.float16), past_key_values=DynamicCache(layers=[<transformers.cache_utils.DynamicLayer object at 0x326f29100>, <transformers.cache_utils.DynamicLayer object at 0x326f2ab10>, <transformers.cache_utils.DynamicLayer object at 0x326f2aab0>, <transformers.cache_utils.DynamicLayer object at 0x326f2ab70>, <transformers.cache_utils.DynamicLayer object at 0x326f2ab40>, <transformers.cache_utils.DynamicLayer object at 0x326f2a750>, <transformers.cache_utils.DynamicLayer object at 0x326f2a6f0>, <transformers.cache_utils.DynamicLayer object at 0x326f2af60>, <transformers.cache_utils.DynamicLayer object at 0x326f2b050>, <transformers.cache_utils.DynamicLayer object at 0x326f2af30>, <transformers.cache_utils.DynamicLayer object at 0x326f2b080>, <transformers.cache_utils.DynamicLayer object at 0x326f2ac90>, <transformers.cache_utils.DynamicLayer object at 0x326f2ac30>, <transformers.cache_utils.DynamicLayer object at 0x326f2a720>, <transformers.cache_utils.DynamicLayer object at 0x326f2b0b0>, <transformers.cache_utils.DynamicLayer object at 0x326f2b170>, <transformers.cache_utils.DynamicLayer object at 0x326f2b1d0>, <transformers.cache_utils.DynamicLayer object at 0x326cf2a80>, <transformers.cache_utils.DynamicLayer object at 0x326f2b3b0>, <transformers.cache_utils.DynamicLayer object at 0x326f2b350>, <transformers.cache_utils.DynamicLayer object at 0x326f2b290>, <transformers.cache_utils.DynamicLayer object at 0x326f2b260>, <transformers.cache_utils.DynamicLayer object at 0x326f29010>, <transformers.cache_utils.DynamicLayer object at 0x326f2ae10>, <transformers.cache_utils.DynamicLayer object at 0x326f29310>, <transformers.cache_utils.DynamicLayer object at 0x326f29f10>, <transformers.cache_utils.DynamicLayer object at 0x326f2a660>, <transformers.cache_utils.DynamicLayer object at 0x326f2b440>, <transformers.cache_utils.DynamicLayer object at 0x326f2b3e0>, <transformers.cache_utils.DynamicLayer object at 0x326f2b710>, <transformers.cache_utils.DynamicLayer object at 0x326f2b470>, <transformers.cache_utils.DynamicLayer object at 0x326f2b740>]), hidden_states=None, attentions=None)
seem like "hidden_states" is always None

[meegle84]

same error here

[meegle84]

@loscrossos the issue form

Describe the bug
After clicking "Start Generation" button, an error occurred.
TypeError: 'NoneType' object is not subscriptable

To Reproduce
First of all I use an script to run the app:

#!/usr/bin/env bash
#https://github.com/loscrossos/core_framepackstudio
python3.12 -m venv venv
source venv/bin/activate
python3.12 -m pip install --upgrade pip
python3.12 -m pip install -r requirements.txt

# create configmodel.txt if it doesn't exist
python3.12 appframepack.py --checkmodels
python3.12 appf1framepack.py --checkmodels

# run once to print system report
#python3.12 appframepack.py --sysreport

# Original FramePack
python3.12 appframepack.py --inbrowser
# F1 FramePack
#python3.12 appf1framepack.py --inbrowser
# FramePack Studio
#python3.12 appstudio.py --inbrowser
source deactivate

1. Execute ./run.sh everything starts ok.
2. Add an input image.
3. Change Total Video Length (Seconds) to 1.
4. Add prompt blink one eye.
5. Push Start Generation button.

Expected behavior
The video generation should start without errors.

Additional context
MacBook Pro M1 Pro 16GB
MacOS Ventura 13.7.6

Screenshots
None

System (please complete the following information):

python appframepack.py --sysreport
================================================================================
TROUBLESHOOTING REPORT - Generated on 2025-08-26 11:22:30
HARDWARE INFORMATION

CPU:
  Model: arm
  Max Frequency: 3228.00 MHz
  Cores: Physical: 10, Logical: 10

RAM:
  Total: 16.00 GB: free: 9.87 used: 4.34 GB

GPU:

DISK:
  Total: 463.18 GB.  Free: 153.33 GB, Used: 8.70 GB

================================================================================
SOFTWARE INFORMATION

OPERATING SYSTEM:
  System: Darwin
  Release: 22.6.0
  Version: Darwin Kernel Version 22.6.0: Thu Apr 24 20:19:51 PDT 2025; root:xnu-8796.141.3.712.2~1/RELEASE_ARM64_T6000
  Machine: arm64

PYTHON:
  Version: 3.12.11
  Implementation: CPython
  Executable: /Volumes/AI/core_framepackstudio/venv/bin/python3.12

INSTALLED PACKAGES (pip freeze):
accelerate==1.10.0
aiofiles==24.1.0
annotated-types==0.7.0
anyio==4.10.0
av==15.0.0
Brotli==1.1.0
certifi==2025.8.3
charset-normalizer==3.4.3
click==8.2.1
diffusers==0.35.0
einops==0.8.1
fastapi==0.116.1
ffmpy==0.6.1
filelock==3.19.1
fsspec==2025.7.0
gradio==5.43.1
gradio_client==1.12.1
groovy==0.1.2
h11==0.16.0
hf-xet==1.1.8
httpcore==1.0.9
httpx==0.28.1
huggingface-hub==0.34.4
idna==3.10
importlib_metadata==8.7.0
Jinja2==3.1.6
markdown-it-py==4.0.0
MarkupSafe==3.0.2
mdurl==0.1.2
mpmath==1.3.0
networkx==3.5
numpy==2.2.6
opencv-contrib-python==4.12.0.88
orjson==3.11.2
packaging==25.0
pandas==2.3.1
peft==0.17.0
pillow==11.3.0
psutil==7.0.0
pydantic==2.11.7
pydantic_core==2.33.2
pydub==0.25.1
Pygments==2.19.2
python-dateutil==2.9.0.post0
python-dotenv==1.1.1
python-multipart==0.0.20
pytz==2025.2
PyYAML==6.0.2
regex==2025.7.34
requests==2.32.5
rich==14.1.0
ruff==0.12.9
safehttpx==0.1.6
safetensors==0.6.2
scipy==1.16.1
semantic-version==2.10.0
sentencepiece==0.2.1
setuptools==80.9.0
shellingham==1.5.4
six==1.17.0
sniffio==1.3.1
starlette==0.47.2
sympy==1.14.0
tokenizers==0.21.4
tomlkit==0.13.3
torch==2.8.0
torchsde==0.2.6
torchvision==0.23.0
tqdm==4.67.1
trampoline==0.1.2
transformers==4.55.2
typer==0.16.1
typing-inspection==0.4.1
typing_extensions==4.14.1
tzdata==2025.2
urllib3==2.5.0
uvicorn==0.35.0
websockets==15.0.1
zipp==3.23.0

CUDA INFORMATION:
NVCC not found in PATH

PYTORCH CUDA:
  PyTorch version: 2.8.0
  CUDA available: False

================================================================================
MODEL CONFIGURATION
Content of configmodel.txt:

PATH_MODEL_FLUX_REDUX_BFL = ./models/flux_redux_bfl
PATH_MODEL_FRAMEPACKI2V_HY = ./models/FramePackI2V_HY
PATH_MODEL_HUNYUANVIDEO = ./models/HunyuanVideo
PATH_MODEL_FRAMEPACK_F1_I2V_HY_20250503 = ./models/FramePack_F1_I2V_HY_20250503
PATH_NEEDED_HF_HOME = ./models/hf_download
DEBUG_MODE = False


================================================================================
RELEVANT ENVIRONMENT VARIABLES
PATH: /Volumes/AI/core_framepackstudio/venv/bin:/Users/<USER>/bin:/Users/<USER>/.local/bin:/usr/local/bin:/usr/local/sbin [following variables not relevant]
VIRTUAL_ENV: /Volumes/AI/core_framepackstudio/venv

================================================================================
ADDITIONAL SYSTEM INFORMATION

Container/Virtualization:
END OF REPORT
================================================================================

Brave Browser 1.80.124 (Build oficial) (arm64)
Chromium: 138.0.7204.168

Error log (paste the console output with the error):

./run.sh                              
Requirement already satisfied: pip in ./venv/lib/python3.12/site-packages (25.2)
Looking in indexes: https://pypi.org/simple, https://download.pytorch.org/whl/nightly/cpu, https://download.pytorch.org/whl/cu128
Ignoring xformers: markers 'sys_platform != "darwin"' don't match your environment
Ignoring triton: markers 'sys_platform == "win32"' don't match your environment
Ignoring triton-windows: markers 'sys_platform == "win32"' don't match your environment
Ignoring triton: markers 'sys_platform == "linux"' don't match your environment
Ignoring flash-attn: markers 'sys_platform == "linux"' don't match your environment
Ignoring flash-attn: markers 'sys_platform == "win32"' don't match your environment
Ignoring sageattention: markers 'sys_platform == "win32"' don't match your environment
Ignoring sageattention: markers 'sys_platform == "linux"' don't match your environment
Requirement already satisfied: torch in ./venv/lib/python3.12/site-packages (from -r requirements.txt (line 6)) (2.8.0)
Requirement already satisfied: torchvision in ./venv/lib/python3.12/site-packages (from -r requirements.txt (line 7)) (0.23.0)
Requirement already satisfied: accelerate in ./venv/lib/python3.12/site-packages (from -r requirements.txt (line 27)) (1.10.0)
Requirement already satisfied: diffusers in ./venv/lib/python3.12/site-packages (from -r requirements.txt (line 28)) (0.35.0)
Requirement already satisfied: transformers in ./venv/lib/python3.12/site-packages (from -r requirements.txt (line 29)) (4.55.2)
Requirement already satisfied: gradio in ./venv/lib/python3.12/site-packages (from -r requirements.txt (line 30)) (5.43.1)
Requirement already satisfied: sentencepiece in ./venv/lib/python3.12/site-packages (from -r requirements.txt (line 31)) (0.2.1)
Requirement already satisfied: pillow in ./venv/lib/python3.12/site-packages (from -r requirements.txt (line 32)) (11.3.0)
Requirement already satisfied: av in ./venv/lib/python3.12/site-packages (from -r requirements.txt (line 33)) (15.0.0)
Requirement already satisfied: numpy in ./venv/lib/python3.12/site-packages (from -r requirements.txt (line 34)) (2.2.6)
Requirement already satisfied: scipy in ./venv/lib/python3.12/site-packages (from -r requirements.txt (line 35)) (1.16.1)
Requirement already satisfied: requests in ./venv/lib/python3.12/site-packages (from -r requirements.txt (line 36)) (2.32.5)
Requirement already satisfied: torchsde in ./venv/lib/python3.12/site-packages (from -r requirements.txt (line 37)) (0.2.6)
Requirement already satisfied: einops in ./venv/lib/python3.12/site-packages (from -r requirements.txt (line 63)) (0.8.1)
Requirement already satisfied: opencv-contrib-python in ./venv/lib/python3.12/site-packages (from -r requirements.txt (line 64)) (4.12.0.88)
Requirement already satisfied: safetensors in ./venv/lib/python3.12/site-packages (from -r requirements.txt (line 65)) (0.6.2)
Requirement already satisfied: python-dotenv in ./venv/lib/python3.12/site-packages (from -r requirements.txt (line 66)) (1.1.1)
Requirement already satisfied: jinja2>=3.1.2 in ./venv/lib/python3.12/site-packages (from -r requirements.txt (line 67)) (3.1.6)
Requirement already satisfied: peft in ./venv/lib/python3.12/site-packages (from -r requirements.txt (line 68)) (0.17.0)
Requirement already satisfied: psutil in ./venv/lib/python3.12/site-packages (from -r requirements.txt (line 69)) (7.0.0)
Requirement already satisfied: filelock in ./venv/lib/python3.12/site-packages (from torch->-r requirements.txt (line 6)) (3.19.1)
Requirement already satisfied: typing-extensions>=4.10.0 in ./venv/lib/python3.12/site-packages (from torch->-r requirements.txt (line 6)) (4.14.1)
Requirement already satisfied: setuptools in ./venv/lib/python3.12/site-packages (from torch->-r requirements.txt (line 6)) (80.9.0)
Requirement already satisfied: sympy>=1.13.3 in ./venv/lib/python3.12/site-packages (from torch->-r requirements.txt (line 6)) (1.14.0)
Requirement already satisfied: networkx in ./venv/lib/python3.12/site-packages (from torch->-r requirements.txt (line 6)) (3.5)
Requirement already satisfied: fsspec in ./venv/lib/python3.12/site-packages (from torch->-r requirements.txt (line 6)) (2025.7.0)
Requirement already satisfied: packaging>=20.0 in ./venv/lib/python3.12/site-packages (from accelerate->-r requirements.txt (line 27)) (25.0)
Requirement already satisfied: pyyaml in ./venv/lib/python3.12/site-packages (from accelerate->-r requirements.txt (line 27)) (6.0.2)
Requirement already satisfied: huggingface_hub>=0.21.0 in ./venv/lib/python3.12/site-packages (from accelerate->-r requirements.txt (line 27)) (0.34.4)
Requirement already satisfied: importlib_metadata in ./venv/lib/python3.12/site-packages (from diffusers->-r requirements.txt (line 28)) (8.7.0)
Requirement already satisfied: regex!=2019.12.17 in ./venv/lib/python3.12/site-packages (from diffusers->-r requirements.txt (line 28)) (2025.7.34)
Requirement already satisfied: tokenizers<0.22,>=0.21 in ./venv/lib/python3.12/site-packages (from transformers->-r requirements.txt (line 29)) (0.21.4)
Requirement already satisfied: tqdm>=4.27 in ./venv/lib/python3.12/site-packages (from transformers->-r requirements.txt (line 29)) (4.67.1)
Requirement already satisfied: hf-xet<2.0.0,>=1.1.3 in ./venv/lib/python3.12/site-packages (from huggingface_hub>=0.21.0->accelerate->-r requirements.txt (line 27)) (1.1.8)
Requirement already satisfied: aiofiles<25.0,>=22.0 in ./venv/lib/python3.12/site-packages (from gradio->-r requirements.txt (line 30)) (24.1.0)
Requirement already satisfied: anyio<5.0,>=3.0 in ./venv/lib/python3.12/site-packages (from gradio->-r requirements.txt (line 30)) (4.10.0)
Requirement already satisfied: brotli>=1.1.0 in ./venv/lib/python3.12/site-packages (from gradio->-r requirements.txt (line 30)) (1.1.0)
Requirement already satisfied: fastapi<1.0,>=0.115.2 in ./venv/lib/python3.12/site-packages (from gradio->-r requirements.txt (line 30)) (0.116.1)
Requirement already satisfied: ffmpy in ./venv/lib/python3.12/site-packages (from gradio->-r requirements.txt (line 30)) (0.6.1)
Requirement already satisfied: gradio-client==1.12.1 in ./venv/lib/python3.12/site-packages (from gradio->-r requirements.txt (line 30)) (1.12.1)
Requirement already satisfied: groovy~=0.1 in ./venv/lib/python3.12/site-packages (from gradio->-r requirements.txt (line 30)) (0.1.2)
Requirement already satisfied: httpx<1.0,>=0.24.1 in ./venv/lib/python3.12/site-packages (from gradio->-r requirements.txt (line 30)) (0.28.1)
Requirement already satisfied: markupsafe<4.0,>=2.0 in ./venv/lib/python3.12/site-packages (from gradio->-r requirements.txt (line 30)) (3.0.2)
Requirement already satisfied: orjson~=3.0 in ./venv/lib/python3.12/site-packages (from gradio->-r requirements.txt (line 30)) (3.11.2)
Requirement already satisfied: pandas<3.0,>=1.0 in ./venv/lib/python3.12/site-packages (from gradio->-r requirements.txt (line 30)) (2.3.1)
Requirement already satisfied: pydantic<2.12,>=2.0 in ./venv/lib/python3.12/site-packages (from gradio->-r requirements.txt (line 30)) (2.11.7)
Requirement already satisfied: pydub in ./venv/lib/python3.12/site-packages (from gradio->-r requirements.txt (line 30)) (0.25.1)
Requirement already satisfied: python-multipart>=0.0.18 in ./venv/lib/python3.12/site-packages (from gradio->-r requirements.txt (line 30)) (0.0.20)
Requirement already satisfied: ruff>=0.9.3 in ./venv/lib/python3.12/site-packages (from gradio->-r requirements.txt (line 30)) (0.12.9)
Requirement already satisfied: safehttpx<0.2.0,>=0.1.6 in ./venv/lib/python3.12/site-packages (from gradio->-r requirements.txt (line 30)) (0.1.6)
Requirement already satisfied: semantic-version~=2.0 in ./venv/lib/python3.12/site-packages (from gradio->-r requirements.txt (line 30)) (2.10.0)
Requirement already satisfied: starlette<1.0,>=0.40.0 in ./venv/lib/python3.12/site-packages (from gradio->-r requirements.txt (line 30)) (0.47.2)
Requirement already satisfied: tomlkit<0.14.0,>=0.12.0 in ./venv/lib/python3.12/site-packages (from gradio->-r requirements.txt (line 30)) (0.13.3)
Requirement already satisfied: typer<1.0,>=0.12 in ./venv/lib/python3.12/site-packages (from gradio->-r requirements.txt (line 30)) (0.16.1)
Requirement already satisfied: uvicorn>=0.14.0 in ./venv/lib/python3.12/site-packages (from gradio->-r requirements.txt (line 30)) (0.35.0)
Requirement already satisfied: websockets<16.0,>=10.0 in ./venv/lib/python3.12/site-packages (from gradio-client==1.12.1->gradio->-r requirements.txt (line 30)) (15.0.1)
Requirement already satisfied: idna>=2.8 in ./venv/lib/python3.12/site-packages (from anyio<5.0,>=3.0->gradio->-r requirements.txt (line 30)) (3.10)
Requirement already satisfied: sniffio>=1.1 in ./venv/lib/python3.12/site-packages (from anyio<5.0,>=3.0->gradio->-r requirements.txt (line 30)) (1.3.1)
Requirement already satisfied: certifi in ./venv/lib/python3.12/site-packages (from httpx<1.0,>=0.24.1->gradio->-r requirements.txt (line 30)) (2025.8.3)
Requirement already satisfied: httpcore==1.* in ./venv/lib/python3.12/site-packages (from httpx<1.0,>=0.24.1->gradio->-r requirements.txt (line 30)) (1.0.9)
Requirement already satisfied: h11>=0.16 in ./venv/lib/python3.12/site-packages (from httpcore==1.*->httpx<1.0,>=0.24.1->gradio->-r requirements.txt (line 30)) (0.16.0)
Requirement already satisfied: python-dateutil>=2.8.2 in ./venv/lib/python3.12/site-packages (from pandas<3.0,>=1.0->gradio->-r requirements.txt (line 30)) (2.9.0.post0)
Requirement already satisfied: pytz>=2020.1 in ./venv/lib/python3.12/site-packages (from pandas<3.0,>=1.0->gradio->-r requirements.txt (line 30)) (2025.2)
Requirement already satisfied: tzdata>=2022.7 in ./venv/lib/python3.12/site-packages (from pandas<3.0,>=1.0->gradio->-r requirements.txt (line 30)) (2025.2)
Requirement already satisfied: annotated-types>=0.6.0 in ./venv/lib/python3.12/site-packages (from pydantic<2.12,>=2.0->gradio->-r requirements.txt (line 30)) (0.7.0)
Requirement already satisfied: pydantic-core==2.33.2 in ./venv/lib/python3.12/site-packages (from pydantic<2.12,>=2.0->gradio->-r requirements.txt (line 30)) (2.33.2)
Requirement already satisfied: typing-inspection>=0.4.0 in ./venv/lib/python3.12/site-packages (from pydantic<2.12,>=2.0->gradio->-r requirements.txt (line 30)) (0.4.1)
Requirement already satisfied: click>=8.0.0 in ./venv/lib/python3.12/site-packages (from typer<1.0,>=0.12->gradio->-r requirements.txt (line 30)) (8.2.1)
Requirement already satisfied: shellingham>=1.3.0 in ./venv/lib/python3.12/site-packages (from typer<1.0,>=0.12->gradio->-r requirements.txt (line 30)) (1.5.4)
Requirement already satisfied: rich>=10.11.0 in ./venv/lib/python3.12/site-packages (from typer<1.0,>=0.12->gradio->-r requirements.txt (line 30)) (14.1.0)
Requirement already satisfied: charset_normalizer<4,>=2 in ./venv/lib/python3.12/site-packages (from requests->-r requirements.txt (line 36)) (3.4.3)
Requirement already satisfied: urllib3<3,>=1.21.1 in ./venv/lib/python3.12/site-packages (from requests->-r requirements.txt (line 36)) (2.5.0)
Requirement already satisfied: trampoline>=0.1.2 in ./venv/lib/python3.12/site-packages (from torchsde->-r requirements.txt (line 37)) (0.1.2)
Requirement already satisfied: six>=1.5 in ./venv/lib/python3.12/site-packages (from python-dateutil>=2.8.2->pandas<3.0,>=1.0->gradio->-r requirements.txt (line 30)) (1.17.0)
Requirement already satisfied: markdown-it-py>=2.2.0 in ./venv/lib/python3.12/site-packages (from rich>=10.11.0->typer<1.0,>=0.12->gradio->-r requirements.txt (line 30)) (4.0.0)
Requirement already satisfied: pygments<3.0.0,>=2.13.0 in ./venv/lib/python3.12/site-packages (from rich>=10.11.0->typer<1.0,>=0.12->gradio->-r requirements.txt (line 30)) (2.19.2)
Requirement already satisfied: mdurl~=0.1 in ./venv/lib/python3.12/site-packages (from markdown-it-py>=2.2.0->rich>=10.11.0->typer<1.0,>=0.12->gradio->-r requirements.txt (line 30)) (0.1.2)
Requirement already satisfied: mpmath<1.4,>=1.1.0 in ./venv/lib/python3.12/site-packages (from sympy>=1.13.3->torch->-r requirements.txt (line 6)) (1.3.0)
Requirement already satisfied: zipp>=3.20 in ./venv/lib/python3.12/site-packages (from importlib_metadata->diffusers->-r requirements.txt (line 28)) (3.23.0)
CROSSOS_FILE_CHECK: checking model accessibility

-Searching Group1: Model HF_HOME----------------------------------------------
[!FOUND!]: ./models/hf_download/hub/models--hunyuanvideo-community--HunyuanVideo/
[MISSING]: ./models/hf_download/hub/models--lllyasviel--FramePack_F1_I2V_HY_20250503/
[!FOUND!]: ./models/hf_download/hub/models--lllyasviel--FramePackI2V_HY/
[!FOUND!]: ./models/hf_download/hub/models--lllyasviel--flux_redux_bfl/
-Searching Group2: Manual Model Directories-----------------------------------
[!FOUND!]: ./models/HunyuanVideo
[!FOUND!]: ./models/FramePack_F1_I2V_HY_20250503
[!FOUND!]: ./models/FramePackI2V_HY
[!FOUND!]: ./models/flux_redux_bfl
-Searching Group3: Needed Directories-----------------------------------------
[!FOUND!]: ./models/hf_download
-checking explicite Files---------------------------------------------------


-Needed Paths---------------------------------------------------
All Needed PATHS exist.
-Needed Models--------------------------------------------------
Some HF_Download models were found. Some might need to be downloaded!
RESULT: It seems all models were found. Nothing will be downloaded!
CROSSOS_FILE_CHECK: checking model accessibility

-Searching Group1: Model HF_HOME----------------------------------------------
[!FOUND!]: ./models/hf_download/hub/models--lllyasviel--FramePackI2V_HY/
[!FOUND!]: ./models/hf_download/hub/models--hunyuanvideo-community--HunyuanVideo/
[MISSING]: ./models/hf_download/hub/models--lllyasviel--FramePack_F1_I2V_HY_20250503/
[!FOUND!]: ./models/hf_download/hub/models--lllyasviel--flux_redux_bfl/
-Searching Group2: Manual Model Directories-----------------------------------
[!FOUND!]: ./models/FramePackI2V_HY
[!FOUND!]: ./models/HunyuanVideo
[!FOUND!]: ./models/FramePack_F1_I2V_HY_20250503
[!FOUND!]: ./models/flux_redux_bfl
-Searching Group3: Needed Directories-----------------------------------------
[!FOUND!]: ./models/hf_download
-checking explicite Files---------------------------------------------------


-Needed Paths---------------------------------------------------
All Needed PATHS exist.
-Needed Models--------------------------------------------------
Some HF_Download models were found. Some might need to be downloaded!
RESULT: It seems all models were found. Nothing will be downloaded!
Currently enabled native sdp backends: []
Xformers is not installed!
Flash Attn is not installed!
Sage Attn is not installed!
Free VRAM 10.666671752929688 GB. High-VRAM Mode: False
Loading checkpoint shards: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████| 4/4 [00:00<00:00, 26.06it/s]
Loading checkpoint shards: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████| 3/3 [00:00<00:00, 10.70it/s]
* Running on local URL:  http://0.0.0.0:7860
* To create a public link, set `share=True` in `launch()`.
Removing model from memory: DynamicSwap_LlamaModel
Removing model from memory: CLIPTextModel
Removing model from memory: SiglipVisionModel
Removing model from memory: AutoencoderKLHunyuanVideo
Removing model from memory: DynamicSwap_HunyuanVideoTransformer3DModelPacked
Loading model to memory(mps): CLIPTextModel
Traceback (most recent call last):
  File "/Volumes/AI/core_framepackstudio/appframepack.py", line 873, in worker
    llama_vec, clip_l_pooler = encode_prompt_conds(prompt, text_encoder, text_encoder_2, tokenizer, tokenizer_2)
                               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Volumes/AI/core_framepackstudio/venv/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 120, in decorate_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/Volumes/AI/core_framepackstudio/diffusers_helper/hunyuan.py", line 39, in encode_prompt_conds
    llama_vec = llama_outputs.hidden_states[-3][:, crop_start:llama_attention_length]
                ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^
TypeError: 'NoneType' object is not subscriptable
Removing model from memory: CLIPTextModel
Removing model from memory: DynamicSwap_LlamaModel
Removing model from memory: CLIPTextModel
Removing model from memory: SiglipVisionModel
Removing model from memory: AutoencoderKLHunyuanVideo
Removing model from memory: DynamicSwap_HunyuanVideoTransformer3DModelPacked

[loscrossos]

hey @meegle84
thanks for the information. i see two issues:

first: your start script is not optimal if you use it everytime to start the app.
that script bsically installs the whole app AND it starts all three apps (F, F1, FS) everytime you want to start.
that is too much. the script is well made for installation but only to start you need to activate the venv and start one app.

second: the bug itself:
thanks to your description i will run a debug trial next week. first i have to finnish another project that might also make your life easier with the first issue :)

[meegle84]

Hi @loscrossos
I just created a separated issue (before reading your answer) to have a better information starting point, the new one has the corect title, and the correct content of the issue at first message, If you think is redundant you can delete the new one, or link it to this issue.

In the other hand, the script has commented parts and I do not do reinstallation every time, It had been uncommented only to get a better full output to refer to the issue, in other words, I only execute this:

#!/usr/bin/env bash
#https://github.com/loscrossos/core_framepackstudio
python3.12 -m venv venv
source venv/bin/activate
python3.12 appframepack.py --inbrowser
source deactivate

take your time, no hurry, thanks for your reply