Comments (11)
Can you share your workflow and inputs? Thanks!
from comfyui-layerdiffuse.
ComfyUI a38b9b3 2024-03-05 02:24:08
ComfyUI-layerdiffusion d7e0bbe
from comfyui-layerdiffuse.
from comfyui-layerdiffuse.
I also encountered the same error, please let me know if you have any solutions, thanks again
from comfyui-layerdiffuse.
I also encountered the same error, please let me know if you have any solutions, thanks again
I suspect it was caused by me updating to the latest Comfyui version. Is this possible?
from comfyui-layerdiffuse.
I also encountered the same error, please let me know if you have any solutions, thanks again我也遇到了同样的错误,请问有解决办法吗,再次感谢
I suspect it was caused by me updating to the latest Comfyui version. Is this possible?我怀疑是我更新到最新的 Comfyui 版本造成的。这可能吗?
Error occurred when executing KSampler:
tuple index out of range
File "/home/h3c/comfyui/ComfyUI/execution.py", line 153, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "/home/h3c/comfyui/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 "/home/h3c/comfyui/ComfyUI/execution.py", line 76, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "/home/h3c/comfyui/ComfyUI/nodes.py", line 1299, in sample
return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise)
File "/home/h3c/comfyui/ComfyUI/nodes.py", line 1269, in common_ksampler
samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
File "/home/h3c/comfyui/ComfyUI/custom_nodes/ComfyUI-AnimateDiff-Evolved/animatediff/sampling.py", line 242, in motion_sample
return orig_comfy_sample(model, noise, *args, **kwargs)
File "/home/h3c/comfyui/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/modules/impact/sample_error_enhancer.py", line 9, in informative_sample
return original_sample(*args, **kwargs) # This code helps interpret error messages that occur within exceptions but does not have any impact on other operations.
File "/home/h3c/comfyui/ComfyUI/comfy/sample.py", line 93, in sample
real_model, positive_copy, negative_copy, noise_mask, models = prepare_sampling(model, noise.shape, positive, negative, noise_mask)
File "/home/h3c/comfyui/ComfyUI/comfy/sample.py", line 86, in prepare_sampling
comfy.model_management.load_models_gpu([model] + models, model.memory_required([noise_shape[0] * 2] + list(noise_shape[1:])) + inference_memory)
File "/home/h3c/comfyui/ComfyUI/comfy/model_management.py", line 410, in load_models_gpu
cur_loaded_model = loaded_model.model_load(lowvram_model_memory)
File "/home/h3c/comfyui/ComfyUI/comfy/model_management.py", line 293, in model_load
raise e
File "/home/h3c/comfyui/ComfyUI/comfy/model_management.py", line 289, in model_load
self.real_model = self.model.patch_model(device_to=patch_model_to) #TODO: do something with loras and offloading to CPU
File "/home/h3c/comfyui/ComfyUI/comfy/model_patcher.py", line 194, in patch_model
out_weight = self.calculate_weight(self.patches[key], temp_weight, key).to(weight.dtype)
File "/home/h3c/comfyui/ComfyUI/custom_nodes/ComfyUI-layerdiffusion-main/layered_diffusion.py", line 28, in calculate_weight
weight = func(self, patches, weight, key)
File "/home/h3c/comfyui/ComfyUI/comfy/model_patcher.py", line 282, in calculate_weight
if v[2] is not None:
from comfyui-layerdiffuse.
ComfyUI a38b9b3 2024-03-05 02:24:08 ComfyUI-layerdiffusion d7e0bbe
I tested your workflow. It seem to work fine in latest version of ComfyUI. In theory the decoded result should have 4 channels. I am going to add an assert message to that check so that we can know more.
from comfyui-layerdiffuse.
layerdiffuse-test.json
ComfyUI a38b9b3 2024-03-05 02:24:08 ComfyUI-layerdiffusion d7e0bbeI tested your workflow. It seem to work fine in latest version of ComfyUI. In theory the decoded result should have 4 channels. I am going to add an assert message to that check so that we can know more.
I switched to comfyui - the cpu is fine
Probably a torch-directml problem
@xuyh1024
from comfyui-layerdiffuse.
put your vae_transparent_decoder.safetensors in \model\layer_model\ ,not in \model\vae
and restart comfyui
from comfyui-layerdiffuse.
Hello everyone,
not really understanding how that thing works. So i've been following two tutorials on Youtube:
https://www.youtube.com/watch?v=aPQ8gvTNCKM
https://www.youtube.com/watch?v=tXO6SJ-6Eb8
I have pasted the needed files in the following folders:
-
Clip
-
Vae
-
Unet
Hers is the source of those files:
https://openart.ai/workflows/maitruclam/comfyui-workflow-for-flux-simple/iuRdGnfzmTbOOzONIiVV
Comfy launch fine with : run_nvidia_gpu.bat
But once i click on Queue Prompt few errors popup:
or occurred when executing CheckpointLoaderSimple:
ERROR: Could not detect model type of: C:\Program Files\AI\ComfyUI_windows_portable\ComfyUI\models\checkpoints\flux1-schnell.safetensors
File "C:\Program Files\AI\ComfyUI_windows_portable\ComfyUI\execution.py", line 152, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\AI\ComfyUI_windows_portable\ComfyUI\execution.py", line 82, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\AI\ComfyUI_windows_portable\ComfyUI\execution.py", line 75, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\AI\ComfyUI_windows_portable\ComfyUI\nodes.py", line 518, in load_checkpoint
out = comfy.sd.load_checkpoint_guess_config(ckpt_path, output_vae=True, output_clip=True, embedding_directory=folder_paths.get_folder_paths("embeddings"))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\AI\ComfyUI_windows_portable\ComfyUI\comfy\sd.py", line 513, in load_checkpoint_guess_config
raise RuntimeError("ERROR: Could not detect model type of: {}".format(ckpt_path))
What am i missing?
Thanks for your help.
from comfyui-layerdiffuse.
I've founded how to make it work, replacing the files in the checkpoint folder (XXX:.......ComfyUI_windows_portable\ComfyUI\models\checkpoints).
I've founded.ckpt files on this website:
https://stable-diffusion-art.com/models/
Now i have a new issue. The final result doesn't show what's describe in the prompt :)
Here are the the settings:
from comfyui-layerdiffuse.
Related Issues (20)
- Is there a tutorial for how to use the layerdiffuse json file in python? HOT 1
- [Bug]: !!! Exception during processing!!! 1024
- Please modify the deprecated API to the recommended version
- How can I use layer diffusion with pose controlnet?
- [Bug]: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! HOT 1
- Can I use my fine-tuned SDXL model with generating imgs from text prompts with transparent backgrounds using layerdiffuse? HOT 1
- [Bug]: Conflict with for_testing/attention_experiments
- No module named 'diffusers.models.unet_2d_blocks' HOT 1
- "Excuse me, what did I do wrong? I don't want this picture.
- [2024-3-9] Generate BG+Blended Given FG" workflow cannot run properly HOT 1
- No module named 'diffusers.models.unet_2d_blocks' Successfully installed diffusers-0.29.0
- When used with the ipadapter, the image cannot be extracted
- LayerDiffusion LayeredDiffusionDecodeRGBA error
- img2img already released, do you notice that ?
- [Bug]: Error when batch size > 5 (SD1.5)
- no module named 'comfy.model_base'
- [Bug]:MACOS BUG:After installing the plugin, when using Karras, black images are obtained starting from the seventh step, with no issues in the sixth step. Currently, I can only resolve the black image issue by using the --force-upcast-attention command. HOT 2
- Given groups=1, weight of size [320, 4, 3, 3], expected input[1, 8, 192, 128] to have 4 channels, but got 8 channels instead HOT 2
- [Bug]: Inference tensors do not track version counter.
- [Bug]: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! (when checking argument for argument mat2 in method wrapper_CUDA_mm)
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-layerdiffuse.