Відео

I was looking around to find how to get rid of duplicated frames and found this. I have to say, you got the idea I need but implemented in an unnecessary complicated way. First of all, you don't need a complicated diagram to load 2 adjacent frames. Just set increment for them seperately starting with 0 and 1, and max value at last frame - 1 and last frame. That will solve the trick. Secondly, to get rid of duplicated frame, just split the result batchs and throw away last frame. After the whole process was done, manually add last frame. That's is alot easier and faster. Too much step will cost more computing power, which is a big deal when we only have a low-end machine.

Hi, super useful. I have this error: # ComfyUI Error Report ## Error Details - **Node Type:** CRMPoseSampler - **Exception Type:** NotImplementedError - **Exception Message:** No operator found for `memory_efficient_attention_forward` with inputs: query : shape=(1, 1024, 1, 512) (torch.float32) key : shape=(1, 1024, 1, 512) (torch.float32) value : shape=(1, 1024, 1, 512) (torch.float32) attn_bias : <class 'NoneType'> p : 0.0 `decoderF` is not supported because: max(query.shape[-1] != value.shape[-1]) > 128 xFormers wasn't build with CUDA support attn_bias type is <class 'NoneType'> operator wasn't built - see `python -m xformers.info` for more info `flshattF@0.0.0` is not supported because: max(query.shape[-1] != value.shape[-1]) > 256 xFormers wasn't build with CUDA support dtype=torch.float32 (supported: {torch.float16, torch.bfloat16}) operator wasn't built - see `python -m xformers.info` for more info `cutlassF` is not supported because: xFormers wasn't build with CUDA support operator wasn't built - see `python -m xformers.info` for more info `smallkF` is not supported because: max(query.shape[-1] != value.shape[-1]) > 32 xFormers wasn't build with CUDA support operator wasn't built - see `python -m xformers.info` for more info unsupported embed per head: 512 ## Stack Trace ```

Hi I cloned KJnodes into custom_nodes folder and did pip install -r requirements.txt and restarted the swarmui, but still I cannot get that grow mask with Blur option. Please help

This has been very useful in the past couple of months. I realised that if you have a video as input or made on the fly (like CogVideo5) you can just feed it into the interpolater and videcombine the output, and that just works without trouble. But I was making a flow that did something to the images and then wanted to interpolate that live, but couldn't work it out. So of course, I can make it save images out and then go through another stage like the above to make the interpolation. What happens is I get loads of tiny videos which are just each batch run of a single frame, what I wanted it to do was interpolate the image sequence and then save the video at the end without it creating the intermediate images.

"Value not in list: model: 'triposr.ckpt' not in (list of length 67) Output will be ignored" what are im doing wrong?

Thanks! Actually this one seems to be working a lot better than Florence 2 for certain things.

the created pictures are getting more and more black. no idea what that is and why.. no matter the prompt. its basically only black with cat eyes at this point

nice video, easy workflow. thx a lot

Can contrôlnet works with schnell model ?

Thnx!

thank you!

is 12GB VRAM enough? i have a rtx 3060, and im using comfyui on archlinux

Hi guys, i need some help too, i meet the issue as below, how can i fix it? TripoSRSampler Cannot handle this data type: (1, 1, 5), |u1 # ComfyUI Error Report ## Error Details - **Node Type:** TripoSRSampler - **Exception Type:** TypeError - **Exception Message:** Cannot handle this data type: (1, 1, 5), |u1 ## Stack Trace ``` File "D:\Flux1\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 323, in execute output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Flux1\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 198, in get_output_data return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Flux1\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 169, in _map_node_over_list process_inputs(input_dict, i) File "D:\Flux1\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 158, in process_inputs results.append(getattr(obj, func)(**inputs)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Flux1\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Flowty-TripoSR\__init__.py", line 92, in sample image = Image.fromarray(np.clip(255. * image, 0, 255).astype(np.uint8)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

Great tutorial, do you happen to know of a way to use this concept/method to continue a previously generated clip output to another one? I'm trying to create a much longer animation out of many shorter ones.

8:35 so that's where the "Auto Queue" people only briefly mention then disappear off the internet forever is!!1!

Hi. Can be used to create a normal infinite zoom between different images without shaking,flickering?

Thank you. But in my case (my setup based on GGUF model/clip) with Neg prompt addition, generation time rises x3 times.

Great, thank you a lot !

How did you use Flux (controlnet) in Stable Diffusion loader?

how to change background with images i mean images from myself ?

Great video! Thanks a lot for this video! Finally I can complete leave A1111.

you can add a simple controlnet behind, it will make things better

Yes! Very useful!!!

Search for: FLUX.1-dev-Controlnet-Inpainting-Alpha

Thx so much !!

good ty

Your videos are great! Maybe another deforum doing controlnet (video) and hybrid video? You Rock!

very useful！！thanks！！♥

This is great, and almost works. I found the final save image box is broken, but reverted to the simple save image. Also, and not your fault of course, my idiocy, I spent ages trying to get the pattern matching , thinking say you have image_00055.png etc, you would have a start seed of 55.. and puzzling how you'd specify 5 digits - then realised it's merely taking any files presumably in sort order, and so seed 0 for that reason.

Couldn't get this to work, please supply the workflow

Hey guys, it seems that the TripoSR addon is broken at the moment. I am quite sure that it has to do with the recent ComfyUI updates. You can try the CRM addon instead but the installation is quite difficult. As soon as I have updates on this I will let you know.

I am getting constant "loading scene" in the viewer and it seems nothing is happening. Please help anybody 🤖

Does anybody know how to solve the problem that the TripoSR viewer says "loading scene" and do nothing? Thanks.

uses 100 % cpu for each frame generation, yikes

Excellent idea my friend ! But is not working for me. I replicate your workflow, with the model TripoSR, but the results are so bad man... in a very poor definition... I tried to modify the parameters, but nothing change... What can i do ?

By lowvram can my 1660 super run it 😢

would this work with flux?

Hello, can you only use other editing software to synthesize the initial video and the video generated by this workflow? Workflow compositing two videos can't be done yet?

How to import IPadapterPlus to Comfyui =((

short and simple... thanks!

it's not working for me (( it's removing only for one image

Is it better than Nf4? Have you tried?

Thank you for your tutorial! i did it!!! looks like you understand the piocess under the hood very good!

Thanks you ! Thanks you !

I did a fresh ComfyUI portable download, but the Canny Edge node is nowhere to be found, also not from the links in your description. Any idea where to get it?

Nice. Do you have a workflow for videos?

Thanks!! Exelent work.

how to put those generated images together into a video?

Is there controlnet and ipadapter for GGUF?

Error : No module named 'controlnet_aux' (ControlNet) (I'm using Flux1-dev-Q4_K_S + comfyUI + Controlnet) There is a error during the node "Canny edge" : "Error occurred when executing CannyEdgePreprocessor : No module named 'controlnet_aux' I re-installed ControlNet auxiliary model manually several times, and updated everything. It didn't change anything.