Comments (18)
Please refer to the many previous comments that explain refiner is not currently supported. Please wait patiently for refiner support. If you do not wish to wait, you are free to fix it yourself.
yeah, I figured it out. the node sees the refiner as a V1 model for some reason. we need to add a flag to modules.jason for it
from ait.
You're not using CLIPTextEncodeSDXLRefiner
what's that? another node? oh nvm, found it
from ait.
this happens when the refiner stage starts
from ait.
I can recreate this error but I'm out of time for tonight to deal with it. I also opened a new repo with just the newly made modules. I put the link in the README.txt. Do the other modules work fine for you?
from ait.
I can recreate this error but I'm out of time for tonight to deal with it. I also opened a new repo with just the newly made modules. I put the link in the README.txt. Do the other modules work fine for you?
yes, it's just the refiner part.
from ait.
Please refer to the many previous comments that explain refiner is not currently supported. Please wait patiently for refiner support. If you do not wish to wait, you are free to fix it yourself.
from ait.
the refiner code has been updated in the sdxl branch. Please checkout and confirm the changes are working if possible and report if anything is still broken. The faster we know everything is testing properly the faster I can merge the branch without problems moving forward.
from ait.
the refiner code has been updated in the sdxl branch. Please checkout and confirm the changes are working if possible and report if anything is still broken. The faster we know everything is testing properly the faster I can merge the branch without problems moving forward.
alright. it still sees the refiner as a V1 model for some reason. changing the inference code wasn't needed. however, I still needed to manually place the .SO file for SDXL
from ait.
You're not using CLIPTextEncodeSDXLRefiner
from ait.
You're not using CLIPTextEncodeSDXLRefiner
okay, now it does this:
Found 3 modules for windows xl sm80 1 1024 unet Using f64294f9bae73c4f742a4f61e8567460d1abefb461c792f69e8922c74331cd27 100%|██████████████████████████████████████████████████████████████████████████████████| 67/67 [00:08<00:00, 10.97it/s] !!! Exception during processing !!! Traceback (most recent call last): File "C:\Users\joker\OneDrive\Desktop\A.I\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "C:\Users\joker\OneDrive\Desktop\A.I\ComfyUI\execution.py", line 81, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) File "C:\Users\joker\OneDrive\Desktop\A.I\ComfyUI\execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) File "C:\Users\joker\OneDrive\Desktop\A.I\ComfyUI\nodes.py", line 1206, in sample return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise) File "C:\Users\joker\OneDrive\Desktop\A.I\ComfyUI\custom_nodes\AIT-sdxl\AITemplate\AITemplate.py", line 171, in common_ksampler samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, File "C:\Users\joker\OneDrive\Desktop\A.I\ComfyUI\custom_nodes\AIT-sdxl\AITemplate\AITemplate.py", line 250, in sample module = AITemplate.loader.filter_modules(AIT_OS, sd, AIT_CUDA, batch_size, resolution, model_type)[0] File "C:\Users\joker\OneDrive\Desktop\A.I\ComfyUI\custom_nodes\AIT-sdxl\AITemplate\ait\load.py", line 75, in filter_modules raise ValueError(f"No modules found for {operating_system} {sd} {cuda} {batch_size} {resolution} {model_type}") ValueError: No modules found for windows xlr sm80 1 1024 unet
from ait.
That is to be expected because the refiner modules have not been added to modules.json yet. The file will be updated soon, I am currently preparing Linux modules to share with FizzleDorf and updating the file. Alternatively you can add an entry manually.
from ait.
That is to be expected because the refiner modules have not been added to modules.json yet. The file will be updated soon, I am currently preparing Linux modules to share with FizzleDorf and updating the file. Alternatively you can add an entry manually.
I see. also still had to manually place the .SO files for XL base, it still makes a 0 byte file by default and needs to be replaced
from ait.
Yes, that is because the modules.json hasn't been updated yet. When everything is complete the sdxl branch will be merged.
from ait.
Yes, that is because the modules.json hasn't been updated yet. When everything is complete the sdxl branch will be merged.
alright, checked out the new changes to modules .JSON, gives a different error:
`100%|██████████████████████████████████████████████████████████████████████████████████| 67/67 [00:08<00:00, 12.30it/s]
Found 3 modules for windows xlr sm80 1 1024 unet
Using f4934a1df4101eb689d3c845dd1f25059cacd6f1f79afbe023c412efd358fbbc
Error: SetConstant did not receive correct number of bytes for unbound constant arange: expected 384 but got 320. Check that the provided tensor's shape is correct.
!!! Exception during processing !!!
Traceback (most recent call last):
File "C:\Users\joker\OneDrive\Desktop\A.I\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "C:\Users\joker\OneDrive\Desktop\A.I\ComfyUI\execution.py", line 81, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "C:\Users\joker\OneDrive\Desktop\A.I\ComfyUI\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "C:\Users\joker\OneDrive\Desktop\A.I\ComfyUI\nodes.py", line 1206, in sample
return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise)
File "C:\Users\joker\OneDrive\Desktop\A.I\ComfyUI\custom_nodes\AIT-sdxl\AITemplate\AITemplate.py", line 171, in common_ksampler
samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
File "C:\Users\joker\OneDrive\Desktop\A.I\ComfyUI\custom_nodes\AIT-sdxl\AITemplate\AITemplate.py", line 274, in sample
AITemplate.unet[module['sha256']] = AITemplate.loader.apply_unet(
File "C:\Users\joker\OneDrive\Desktop\A.I\ComfyUI\custom_nodes\AIT-sdxl\AITemplate\ait\load.py", line 217, in apply_unet
return self.apply(aitemplate_module, ait_params)
File "C:\Users\joker\OneDrive\Desktop\A.I\ComfyUI\custom_nodes\AIT-sdxl\AITemplate\ait\load.py", line 196, in apply
aitemplate_module.set_many_constants_with_tensors(ait_params)
File "C:\Users\joker\OneDrive\Desktop\A.I\ComfyUI\custom_nodes\AIT-sdxl\AITemplate\ait\module\model.py", line 840, in set_many_constants_with_tensors
self.set_many_constants(ait_tensors)
File "C:\Users\joker\OneDrive\Desktop\A.I\ComfyUI\custom_nodes\AIT-sdxl\AITemplate\ait\module\model.py", line 791, in set_many_constants
self.DLL.AITemplateModelContainerSetManyConstants(
File "C:\Users\joker\OneDrive\Desktop\A.I\ComfyUI\custom_nodes\AIT-sdxl\AITemplate\ait\module\model.py", line 212, in _wrapped_func
raise RuntimeError(f"Error in function: {method.name}")
RuntimeError: Error in function: AITemplateModelContainerSetManyConstants
Prompt executed in 25.62 seconds`
from ait.
expected 384 but got 320.
You're not using the refiner model.
from ait.
expected 384 but got 320.
You're not using the refiner model.
yes I am..? isn't it called "stable-diffusion-xl-refiner-1.0"? that's what I'm using..
from ait.
expected 384 but got 320.
You're not using the refiner model.
am I supposed to use "sd_xl_refiner_1.0_0.9vae"?
from ait.
okay, just pulled the new changes to the SDXL branch, it works!
from ait.
Related Issues (20)
- Compilation fails after fb84060 HOT 2
- ""log_vml_cpu" not implemented for 'Half'" when using AITemplate on certain models
- module 'comfy.sd' has no attribute 'ModelPatcher' HOT 1
- Unable to compile modules after update HOT 2
- issue: compatibility patch required HOT 2
- Error Running Workflows HOT 3
- [Bug] ddim, uni_pc, uni_pc_bh2
- [Bug] Conditioning Combine node error
- [Bug] ControlNet issues
- [Bug] LoRA issues
- [Bug] Batch size > 1
- [Bug] LoRAs handled incorrectly
- Issues with Inpainting pipeline
- FreeU support?
- Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! HOT 9
- After the last update, an error occurred. HOT 1
- Missing Nodes after updating HOT 3
- AITemplate -v?
- AITemplate if-else
- Cannot import HOT 1
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 ait.