Comments (11)
Hmm, but I git pulled, and tried the input in my original post, and I still get the same error at line 194, in BatchPoolAnimConditioning
final_conditioning = torch.cat(cond_out, dim=0)
RuntimeError: Sizes of tensors must match except in dimension 0. Expected size 77 but got size 154 for tensor number 15 in the list.
Still seems like a padding issue... I wonder if we can fix this by somehow make CLIP return 157 tokens for the first 15 timestamps?
from comfyui_fizznodes.
I've been encountering this error on a fresh install of ComfyUi and FizzNodes with a newly created workflow:
`Error occurred when executing BatchPromptSchedule:
Sizes of tensors must match except in dimension 0. Expected size 154 but got size 77 for tensor number 336 in the list.`
As a workaround I've been padding my keyframe prompts with something like "Highly Detailed, Highly Detailed, Highly Detailed", so that they all end up 154 size. Hardly an elegant solution but seems to get the job done.
from comfyui_fizznodes.
right on. I made the fix and everything is fine. The fix is in 36ff6a7
from comfyui_fizznodes.
I am having the same issue. When the length of the prompt of each keyframe different too much will trigger this error.
from comfyui_fizznodes.
I am getting reports this is still an issue which is odd because I haven't been proccing this error. This may have to do with using older workflows and the updated nodes still show the same behavior as before. I asked someone to test using "fresh" nodes and copying over the parameters to see if this solves the issue. I am not able to test for most of the day at work unfortunately.
from comfyui_fizznodes.
what triggers it for me is trying to use 'embedding:some.pt' anywhere except for the first prompt.
i tried using the append field, as well as manually putting the embedding in prompts.
File "C:\ComfyUI_windows_portable\ComfyUI\execution.py", line 153, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ComfyUI_windows_portable\ComfyUI\execution.py", line 83, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ComfyUI_windows_portable\ComfyUI\execution.py", line 76, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_FizzNodes\ScheduledNodes.py", line 125, in animate pc = BatchPoolAnimConditioning( pos_cur_prompt, pos_nxt_prompt, weight, clip,) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_FizzNodes\BatchFuncs.py", line 207, in BatchPoolAnimConditioning final_conditioning = torch.cat(cond_out, dim=0) ^^^^^^^^^^^^^^^^^^^^^^^^^^ RuntimeError: Sizes of tensors must match except in dimension 0. Expected size 77 but got size 154 for tensor number 30 in the list.
from comfyui_fizznodes.
try the latest commit that fixes this d9f532a
from comfyui_fizznodes.
I am having the same issue with fresh workflow and all new install. Both the node and the workflow is new and I still get the following error
`Using pytorch attention in VAE
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
Using pytorch attention in VAE
missing {'cond_stage_model.clip_l.logit_scale', 'cond_stage_model.clip_l.text_projection'}
[AnimateDiffEvo] - INFO - Loading motion module mm_sd_v15_v2.safetensors
D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_FizzNodes\BatchFuncs.py:128: FutureWarning: Setting an item of incompatible dtype is deprecated and will raise in a future error of pandas. Value '' has dtype incompatible with float64, please explicitly cast to a compatible dtype first.
cur_prompt_series[f] = ''
D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_FizzNodes\BatchFuncs.py:129: FutureWarning: Setting an item of incompatible dtype is deprecated and will raise in a future error of pandas. Value '' has dtype incompatible with float64, please explicitly cast to a compatible dtype first.
nxt_prompt_series[f] = ''
Requested to load SD1ClipModel
Loading 1 new model
ERROR:root:!!! Exception during processing !!!
ERROR:root:Traceback (most recent call last):
File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 153, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 83, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 76, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_FizzNodes\ScheduledNodes.py", line 125, in animate
pc = BatchPoolAnimConditioning( pos_cur_prompt, pos_nxt_prompt, weight, clip,)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_FizzNodes\BatchFuncs.py", line 218, in BatchPoolAnimConditioning
final_conditioning = torch.cat(cond_out, dim=0)
^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: Sizes of tensors must match except in dimension 0. Expected size 77 but got size 154 for tensor number 26 in the list.
Prompt executed in 128.58 seconds`
from comfyui_fizznodes.
This was actioned yesterday. If there is any further issues report to #46.
from comfyui_fizznodes.
I've been encountering this error on a fresh install of ComfyUi and FizzNodes with a newly created workflow: `Error occurred when executing BatchPromptSchedule:
Sizes of tensors must match except in dimension 0. Expected size 154 but got size 77 for tensor number 336 in the list.`
As a workaround I've been padding my keyframe prompts with something like "Highly Detailed, Highly Detailed, Highly Detailed", so that they all end up 154 size. Hardly an elegant solution but seems to get the job done.
Hi, do you manage to solve the issue using the latest commit without purposely adding unnecessary prompt? I updated to the latest one but is still having the same issue.
from comfyui_fizznodes.
when you updated, did you restart the back-end and refresh the page?
from comfyui_fizznodes.
Related Issues (20)
- Issues with BatchPromptScheduleSDXL-Latent HOT 2
- [Question] Batch on SDXL? HOT 2
- import failed HOT 8
- PromptSchedule & StringSchedule will not replace pw_a / pw_b / pw_c / pw_d placeholders HOT 1
- Batch Prompt Schedule AnemateDiff with SDXL checkpoint not working ? HOT 3
- Need help with syntax in blink girl example HOT 3
- Could we get a option for no prompt weighting? HOT 2
- When using animatediff to test some frames in the middle, how to make it work HOT 1
- if max_size is 0 in some files, thows a warning. HOT 1
- works beautifully - noticed one bug/behavior HOT 2
- Note: NumExpr detected 32 cores but "NUMEXPR_MAX_THREADS" not set, so enforcing safe limit of 8. HOT 1
- dtype float64 HOT 4
- This plugin is really cool! Unfortunately, it doesn't work with ELLA. Do you have any plans to update it in the future? HOT 1
- After the update it becomes: NameError: name 'latents' is not defined HOT 3
- Its back? HOT 2
- Error occurred when executing BatchPromptSchedule: Expecting value: line 1 column 7 (char 6) HOT 4
- String Concatenate node returns trailing comma HOT 2
- When I input 50 for "start_frame", it does not start from the prompt of frame 50, but instead starts from the prompt of frame 0. HOT 2
- FutureWarning: Setting an item of incompatible dtype is deprecated and will raise an error in a future version of pandas. HOT 2
- Import Failed every time, need to "Try Fix" to run it HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from comfyui_fizznodes.