Support me for update
2025/2/8
update v1.5, add word cloud transfer
2024/9/22
Rewrote the edge detection function
and removed the #include "lygia/space/ratio.glsl" line
2024/9/4
update v1.4, automatic edge detection and replacement
2024/8/11
update v1.3. add SDXL upscale and more stable replace bg
2024/7/29
Simple Auto Mask For Videos @SouthbayJa
2024/7/14
update v1.2. Dance References
2024/7/12
For new comfyUI users, check your input model, like Lora. checkpoint, controlnet, aniamtediff, and upscale model, and don't forget to update your comfyUI all. There is a screenshot of the node in the download file for reference.
2024/7/9
Don’t let my reference examples stop you from exploring. In fact, any object can dance, such as water, rocks, clothes, cars, particles, etc.
2024/7/8
Updated download file-1.3, add ColorMod node, modified AnimateDiff node, and added a reference image
2024/7/7
I created a flower collection that might be helpful to you.
I used AE to cut out the character dance and turn it into a black and white mask. If you need skills in this area, just ask ChatGPT. He will teach you how to use AE to turn a video into a black and white mask. This is what I did.
Tips below from:https://civarchive.com/models/372584/ipivs-morph-img2vid-animatediff-lcm-hyper-sd
❗If you are getting an error message CLIP Vision Model not found: /ComfyUI/models/clip_vision folder
CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors download and rename
CLIP-ViT-bigG-14-laion2B-39B-b160k.safetensors download and rename
❗If you are getting an error message IPAdapter model not found:
You are likely missing the IPAdapter model. In ComfyUI Manager Menu click Install Models - Search for ip-adapter_sd15_vit-G.safetensors and click Install.
If installing through Manager doesn't work for some reason you can download the model from Huggingface and drop it into \ComfyUI\models\ipadapter folder.
2024/7/6
Use QRCode Controlnet to control appearance and action, use IPAdapter to control the content and style of conversion.
Description
FAQ
Comments (76)
Looking forward to trying out the new version. 🙌🙌
I am having the following error in the final step Error occurred when executing MiDaS-DepthMapPreprocessor: [Errno 2] No such file or directory: 'D:\\A1111\\ComfyUI_windows_portable_nvidia\\ComfyUI_windows_portable\\ComfyUI\\custom_nodes\\comfyui_controlnet_aux\\ckpts \\lllyasviel\\Annotators\\.cache\\huggingface\\download\\dpt_hybrid-midas-501f0c75.pt.501f0c75b3bca7daec6b3682c5054c09b366765aef6fa3a09d03a5cb4b230853.incomplete'
check your sdxl depth controlnet model
@downpink What models do you use?
@aitestbr474 t2i-adapter-depth-midas-sdxl-1.0.fp16.safetensors
Constantly gives an error. (Error occurred when executing Efficient Loader: 'NoneType' object has no attribute 'lower') vae- yes, skpt- yes, lora- yes. I don’t understand what’s wrong.
Error occurred when executing Efficient Loader: 'NoneType' object has no attribute 'lower' File "C:\Users\taras\AppData\Roaming\StabilityMatrix\Packages\ComfyUI\execution.py", line 152, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "C:\Users\taras\AppData\Roaming\StabilityMatrix\Packages\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:\Users\taras\AppData\Roaming\StabilityMatrix\Packages\ComfyUI\execution.py", line 75, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) File "C:\Users\taras\AppData\Roaming\StabilityMatrix\Packages\ComfyUI\custom_nodes\efficiency-nodes-comfyui\efficiency_nodes.py", line 158, in efficientloader model, clip = load_lora(lora_params, ckpt_name, my_unique_id, cache=lora_cache, ckpt_cache=ckpt_cache, cache_overwrite=True) File "C:\Users\taras\AppData\Roaming\StabilityMatrix\Packages\ComfyUI\custom_nodes\efficiency-nodes-comfyui\tsc_utils.py", line 372, in load_lora lora_model, lora_clip = recursive_load_lora(lora_params, ckpt, clip, id, ckpt_cache, cache_overwrite, folder_paths) File "C:\Users\taras\AppData\Roaming\StabilityMatrix\Packages\ComfyUI\custom_nodes\efficiency-nodes-comfyui\tsc_utils.py", line 366, in recursive_load_lora return recursive_load_lora(lora_params[1:], lora_model, lora_clip, id, ckpt_cache, cache_overwrite, folder_paths) File "C:\Users\taras\AppData\Roaming\StabilityMatrix\Packages\ComfyUI\custom_nodes\efficiency-nodes-comfyui\tsc_utils.py", line 363, in recursive_load_lora lora_model, lora_clip = comfy.sd.load_lora_for_models(ckpt, clip, comfy.utils.load_torch_file(lora_path), strength_model, strength_clip) File "C:\Users\taras\AppData\Roaming\StabilityMatrix\Packages\ComfyUI\comfy\utils.py", line 33, in load_torch_file if ckpt.lower().endswith(".safetensors") or ckpt.lower().endswith(".sft"):
can you share your screenshot? which node get red?
@downpink Efficient Loader red frame
what checkpoint model you use?
I can't upload a screenshot. But this is a node Efficient Loader red frame
https://civitai.com/models/4384/dreamshaper here is the link to the checkpoint
sd 1.5\dreamshaper_8lcm (1) safetensors
Do you think there is an error in the checkpoint? Do you have another one?
@Alexandro43 dm me
just put any checkpoint you want, remove any lora you don't have or change to something else
Same problem and I have everything checked aswel...
Same problem and everything all good and checked. Anyone figured by chance?
Hello everyone! I need help! When running a node IpAdapter Advanced an error occurs: Error occurred when executing IPAdapterAdvanced
Error(s) in loading state_dict for Resampler:
size mismatch for proj_in.weight: copying a param with shape torch.Size([768, 1280]) from checkpoint, the shape in current model is torch.Size([768, 1664]).
File "C:\Users\Media2\Desktop\ComfyUI_windows_portable\ComfyUI\execution.py", line 152, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Media2\Desktop\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:\Users\Media2\Desktop\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:\Users\Media2\Desktop\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_IPAdapter_plus\IPAdapterPlus.py", line 822, in apply_ipadapter
work_model, face_image = ipadapter_execute(work_model, ipadapter_model, clip_vision, **ipa_args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Media2\Desktop\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_IPAdapter_plus\IPAdapterPlus.py", line 441, in ipadapter_execute
ipa = IPAdapter(
^^^^^^^^^^
File "C:\Users\Media2\Desktop\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_IPAdapter_plus\IPAdapterPlus.py", line 71, in init
self.image_proj_model.load_state_dict(ipadapter_model["image_proj"])
File "C:\Users\Media2\Desktop\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 2215, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
run this test workflow ComfyUI\custom_nodes\ComfyUI_IPAdapter_plus\examples\ipadapter_advanced.json, and you will know what happen in your IPAdapter
or maybe you can change the size of your input image
@downpink I changed the size of both the input image and the input video - nothing helps. I've been suffering for 3 days already)))
@downpink thank you very much. I will try
@downpink tried - the same error. I don't understand anything, why it doesn't work
@marchalkoviktor697 if you update you IPAdapter custom node
I think you are using wrong ipadapters in each section. make sure you use 1.5 for 1st,2nd,3rd controlnet and xl for 3rd
@AlDenteArt Can you explain in more detail?
@downpink i updated IPAdapter
Firstly Thank you! love your work.
I was wondering how you made the reference ballerina shot, it isn't the straight white of a typical depth map, I would love to know. Thanks again
use AE made white and black mask
@downpink thank you, got it!
@downpink please simplifie-it for new people . What is AE , please share AE workflow how to take a dancer from a video and cut and cropt it and white it as a white and black mask please
Runway ExtractDepth
Not able to do a test run of 50 frames. Getting the following error:
Error occurred when executing ImageSelector: Index 50 is out of range. Available images: 50 File "/workspace/ComfyUI/execution.py", line 152, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "/workspace/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 "/workspace/ComfyUI/execution.py", line 75, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) File "/workspace/ComfyUI/custom_nodes/ComfyUI-Documents/document_nodes.py", line 192, in select_images raise ValueError(f"Index {idx} is out of range. Available images: {len(images)}")
Tried all the channels (green, blue, red, alpha), but no fix.
If I try to set it to 0 and run, the process gets killed. I'm on a 3090 with 24 GB vram. Any idea why?
bypass the ImageSelector, and try 64 frames, and what size your input vid?
@downpink hey thanks for replying. I got to fix that issue, but now its a new one. it works when im sampling 50 frames. As soon as I try to process the full video (14 seconds), it kills the process. I'm on runpod, using a 4090 24 GB with 30 GB RAM. why is that happening and how can I fix it?
Hi i have this error, someone please can help me?
Error occurred when executing ADE_AnimateDiffLoRALoader: join() argument must be str, bytes, or os.PathLike object, not 'NoneType' File "F:\ComfyUi\ComfyUI_windows_portable\ComfyUI\execution.py", line 152, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\ComfyUi\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 "F:\ComfyUi\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 "F:\ComfyUi\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-AnimateDiff-Evolved\animatediff\nodes_lora.py", line 38, in load_motion_lora lora_path = get_motion_lora_path(name) ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\ComfyUi\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-AnimateDiff-Evolved\animatediff\utils_model.py", line 360, in get_motion_lora_path return folder_paths.get_full_path(Folders.MOTION_LORA, lora_name) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\ComfyUi\ComfyUI_windows_portable\ComfyUI\folder_paths.py", line 186, in get_full_path filename = os.path.relpath(os.path.join("/", filename), "/") ^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "", line 147, in join File "", line 152, in checkarg_types
check if you have animatediff motion lora in your file, using aidma-RUN-Motion Lora
@Meth_ or you can bypass the motion lora loader
I had this same error (or set of errors?) and for me, there were a ton of missing elements. I just went through every node that had anything that needed to be loaded and made sure I had the exact same thing loaded in there. I downloaded probably 8 or 9 different files, including DreamShaper8_LCM, Juggernaut-XL_v9_RunDiffusionPhoto_v2, Ghibli_v6, aidma-RUN-Motion Lora (as downpink already mentioned), hsxl_temporal_layers.f16, control_v11p_sd15_lineart.pth, control_v11f1p_sd16_depth.pth, and t2i-adapter-depth_midas-sdxl-1.0.fp16. I might have missed one in the list, but without ALL of these, I got that same error.
Hi, please how do I make my object dance in a particular place? eg dancing inside a bottle, or on a branch of a tree, instead of using the whole background. I can't seem to get this working. Thank you!
Generate a suitable bottle image as a background, replace first render vid bg
whats funny is , used the project files with same settings and can't get anything far from garbage :(
Hello there, dear friend! After running, I received the following error, but I've checked the model selection settings prior to this sampler and it seems like there shouldn't be any issues. Could you please lend me a hand? I really appreciate it!
Error occurred when executing KSampler (Efficient): 'NoneType' object has no attribute 'shape' File "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\execution.py", line 316, 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 "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\execution.py", line 191, in get_output_data return_values = mapnode_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb) File "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\execution.py", line 168, in mapnode_over_list process_inputs(input_dict, i) File "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\execution.py", line 157, in process_inputs results.append(getattr(obj, func)(**inputs)) File "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\custom_nodes\efficiency-nodes-comfyui\efficiency_nodes.py", line 732, in sample samples, images, gifs, preview = process_latent_image(model, seed, steps, cfg, sampler_name, scheduler, File "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\custom_nodes\efficiency-nodes-comfyui\efficiency_nodes.py", line 550, in process_latent_image samples = KSampler().sample(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, File "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\nodes.py", line 1429, in sample return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise) File "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\nodes.py", line 1396, in common_ksampler samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, File "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\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 "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-AnimateDiff-Evolved\animatediff\sampling.py", line 549, in motion_sample latents = orig_comfy_sample(model, noise, args, *kwargs) File "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-Advanced-ControlNet\adv_control\sampling.py", line 92, in acn_sample return orig_comfy_sample(model, args, *kwargs) File "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-Advanced-ControlNet\adv_control\utils.py", line 112, in uncond_multiplier_check_cn_sample return orig_comfy_sample(model, args, *kwargs) File "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\comfy\sample.py", line 43, in sample samples = sampler.sample(noise, positive, negative, cfg=cfg, latent_image=latent_image, start_step=start_step, last_step=last_step, force_full_denoise=force_full_denoise, denoise_mask=noise_mask, sigmas=sigmas, callback=callback, disable_pbar=disable_pbar, seed=seed) File "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\comfy\samplers.py", line 829, in sample return sample(self.model, noise, positive, negative, cfg, self.device, sampler, sigmas, self.model_options, latent_image=latent_image, denoise_mask=denoise_mask, callback=callback, disable_pbar=disable_pbar, seed=seed) File "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\comfy\samplers.py", line 729, in sample return cfg_guider.sample(noise, latent_image, sampler, sigmas, denoise_mask, callback, disable_pbar, seed) File "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\comfy\samplers.py", line 716, in sample output = self.inner_sample(noise, latent_image, device, sampler, sigmas, denoise_mask, callback, disable_pbar, seed) File "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\comfy\samplers.py", line 695, in inner_sample samples = sampler.sample(self, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar) File "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\comfy\samplers.py", line 600, in sample samples = self.sampler_function(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, **self.extra_options) File "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\python\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context return func(*args, **kwargs) File "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\comfy\k_diffusion\sampling.py", line 779, in sample_lcm denoised = model(x, sigmas[i] s_in, *extra_args) File "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\comfy\samplers.py", line 299, in call out = self.inner_model(x, sigma, model_options=model_options, seed=seed) File "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\comfy\samplers.py", line 682, in call return self.predict_noise(*args, **kwargs) File "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\comfy\samplers.py", line 685, in predict_noise return sampling_function(self.inner_model, x, timestep, self.conds.get("negative", None), self.conds.get("positive", None), self.cfg, model_options=model_options, seed=seed) File "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-AnimateDiff-Evolved\animatediff\sampling.py", line 658, in evolved_sampling_function cond_pred, uncond_pred = sliding_calc_conds_batch(model, [cond, uncond_], x, timestep, model_options) File "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-AnimateDiff-Evolved\animatediff\sampling.py", line 925, in sliding_calc_conds_batch sub_conds_out = calc_cond_uncond_batch_wrapper(model, sub_conds, sub_x, sub_timestep, model_options) File "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-AnimateDiff-Evolved\animatediff\sampling.py", line 1034, in calc_cond_uncond_batch_wrapper return comfy.samplers.calc_cond_batch(model, conds, x_in, timestep, model_options) File "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-TiledDiffusion\.patches.py", line 4, in calc_cond_batch return calc_cond_batch_original_tiled_diffusion_33ffb733(model, conds, x_in, timestep, model_options) File "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\comfy\samplers.py", line 202, in calc_cond_batch c['control'] = control.get_control(input_x, timestep_, c, len(cond_or_uncond)) File "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-Advanced-ControlNet\adv_control\utils.py", line 749, in get_control_inject return self.get_control_advanced(x_noisy, t, cond, batched_number) File "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-Advanced-ControlNet\adv_control\control.py", line 37, in get_control_advanced return self.sliding_get_control(x_noisy, t, cond, batched_number) File "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-Advanced-ControlNet\adv_control\control.py", line 42, in sliding_get_control control_prev = self.previous_controlnet.get_control(x_noisy, t, cond, batched_number) File "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-Advanced-ControlNet\adv_control\utils.py", line 749, in get_control_inject return self.get_control_advanced(x_noisy, t, cond, batched_number) File "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-Advanced-ControlNet\adv_control\control.py", line 37, in get_control_advanced return self.sliding_get_control(x_noisy, t, cond, batched_number) File "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-Advanced-ControlNet\adv_control\control.py", line 93, in sliding_get_control control = self.control_model(x=x_noisy.to(dtype), hint=self.cond_hint, timesteps=timestep.float(), context=context.to(dtype), y=y) File "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\python\lib\site-packages\torch\nn\modules\module.py", line 1532, in wrappedcall_impl return self._call_impl(*args, **kwargs) File "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\python\lib\site-packages\torch\nn\modules\module.py", line 1541, in callimpl return forward_call(*args, **kwargs) File "H:\AI\AI_pain\Comfyui\ComfyUI-aki-v1.3\comfy\cldm\cldm.py", line 420, in forward assert y.shape[0] == x.shape[0]
if you have enough memory? check your controlnet model, use sd1.5 model
and also try to run pip install -r requirement.txt under custom_module/ComfyUI-aki-v1.3
have same problem perhaps the monster sdxl not good for sd 1.5 i will try look if theres 1.5 ver :)
lets try this :
https://huggingface.co/monster-labs/control_v1p_sd15_qrcode_monster/tree/main
Hello, may I ask how to make a rotating wooden frame? It's really impressive
use blender
Hello friend! What adaptations do I need to make to use it correctly in the SDXL version?
v1.3 can upscale by SDXL
Failed to validate prompt for output 228: * LoRA Stacker 187: - Value not in list: lora_name_2: '1.5\Floweria_yiu_v10.safetensors' not in (list of length 84)
have you solve? I also got this issue, bypass the lora stacker or restart comfyui can help
Replace it by the new one LoRa Staker, and it will work
add another lora and connect it to the left :)
@downpink no if the segmentaion not good it wont work good i need to know please how to mask with opacy less than 100 and save as mp4 without loosing quality exactley as the female dancer . i did try with SAM2 i was able to seg but the line art bad the mask bad the opacity bad please share wf how to do it
@downpink So I found the reason is you're json workflow has lora included in the lora stacker json file that doesn't even show in the lora stacker, if you change the lora_count to 2 you'll see what it's pointing too and you can change the lora name to something you have and lower it to 1 or keep it.
Or replace it but that didn't work for me.
@dmitlenko This solution worked. Thank You
hey, my man! I really like the composition in the preview node. But it looks bad in 1.5 and sdxl nodes. What to do to get the closer results like in the preview node? Apply the same settings in all ksampler efficient nodes?
you can try download v1.0 workflow, it's upscale base on preview
@downpink thanks. By the way, what settings are responsible for more explicit merging of bg image and main image?
@workingking07I guess you want the sway of the waves? you can disconnect the mask of Ipadapter Advance node, and just use qr controlnet
@downpink yeah, dancing in the waves) Your advise helped a bit and it merged good after discinecting a mask, but waves are more look now like a boiling soapy water) how to back waves to life like in the preview?) On the preview with default workflow settings it was good. I actually tried the v 1.0, and it generates good, but way too dark videos.
ok, you can add seawater img in ipadapter and set qr controlnet 0.5/0.65, set empty Latent image to 480 * 854, no need upscale node, remember use correct Prompt
Hello, I encountered this problem. Please help me. Excuse me.
Error occurred when executing VHS_VideoCombine:
ffmpeg is required for video outputs and could not be found.
In order to use video outputs, you must either:
- Install imageio-ffmpeg with pip,
- Place a ffmpeg executable in D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable, or
- Install ffmpeg and add it to the system path.
File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 316, 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:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 191, in get_output_data
return_values = mapnode_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:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 168, in mapnode_over_list
process_inputs(input_dict, i)
File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 157, in process_inputs
results.append(getattr(obj, func)(**inputs))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-VideoHelperSuite\videohelpersuite\nodes.py", line 382, in combine_video
raise ProcessLookupError(f"ffmpeg is required for video outputs and could not be found.\nIn order to use video outputs, you must either:\n- Install imageio-ffmpeg with pip,\n- Place a ffmpeg executable in {os.path.abspath('')}, or\n- Install ffmpeg and add it to the system path.")
Hello author, the video I produced using your workflow is blurry and the background keeps flickering. What is the reason? Thank you
please share your result
Of course, I have shared my video output, and I hope to get your guidance, thank you.
@downpink Of course, I have shared my video output, and I hope to get your guidance, thank you.
@siqiao46528 What's your checkpoint model? you should use LCM model in first Efficient Loader
there is a screenshot in workflow download file, you can see my setting
@downpink I'm using the exact same model as yours, which is what confuses me. If possible, could you share a picture of the glass bottles and the glass frame with the other plants? I can try another combination. Thanks
@siqiao46528 but why? can you share your screenshot? bottle picture had been shared