Thanks for the tutorial, I was able to set up everything accordingly. But I am getting this error at 73% SamplerCustomAdvanced expected scalar type Half but found BFloat16. Please help :)
@@AiMotionStudio I redownloaded ComfyUI, and re-did the whole process. It is Comfy 2.0, still same error :( Maybe it's the lack of vram? I have a 2080 Super. I tried using GGUF models as well.
We were able to fix this error using this: github.com/comfyanonymous/ComfyUI/issues/5601 just go to your E:\pinokio\api\comfyui.git\app\comfy\ldm\flux folder and edit the model file with notepad+ and search for "out = self.forward_orig" line 184 and remove ", transformer_options" at the end of that line and save changes this will fix this errors
@@AiMotionStudio after having some problems I reinstalled python and comfy I have to install pulid rn but when I try to install for example C:\Users\user\Desktop\ComfyUI_windows_portable\python_embeded\Scripts\python.exe -m pip install C:\Users\user\Desktop\ComfyUI_windows_portable\ComfyUI\insightface-0.7.3-cp312-cp312-win_amd64.whl onnxruntime this insight face I get this C:\Users\user\Desktop\ComfyUI_windows_portable\python_embeded\Scripts\python.exe' is not recognized as an internal or external command,operable program or batch file. same for requirements.txt as well
Hello, I hope you can help me because I get an error when I start CMD. I get "git" which is not recognized as an internal or external command, program or executable batch file. I hope you can help me. I have the latest version of comfyui installed on pinokio.
most people find it working after they installed the latest version of comfyui 2.0. i think the problem is with the old comfyui had not fixed the torch pip errors that usually comes with using comfyui. Try to check on the video again, follow all the steps and instal the latest Comfyui. hopefully it will fix the issues. Let me know if you have any other questions.
This is a problem with comfyui. If you revert to the old version, the problem will be gone. Go to the comfyui directory and run "git reset --hard cc9cf6d1bd957d764ad418258b61d7e08187573b"
@@murattuanaahmet Hello! Thanks for the recommendation, in my case the problem was in the python version, after updating it everything worked, but I couldn't achieve such similarity as the video, in principle it works at the level of Stable Diffusion Insta Swap or Reactor.
We were able to fix this error using this: github.com/comfyanonymous/ComfyUI/issues/5601 just go to your E:\pinokio\api\comfyui.git\app\comfy\ldm\flux folder and edit the model file with notepad+ and search for "out = self.forward_orig" line 184 and remove ", transformer_options" at the end of that line and save changes this will fix this errors
I could not achieve facial consistency in my experiments. I think the resolution of the reference image I use has an effect on this. Can you give information about the size of the reference images you use?
Flux Pulid is a lora replacement, so you don't have to train lora for hours, with pulid you can instantly generate a consistent face with just one reference image.
I have downloaded the pulid model safetensors and placed it in the Pulid folder. But why does it always stop at the flux model Puled node? Failed to validate the prompt for output 9: * PulidFluxModelLoader 99: - Value not in list: pulid_file: 'pulid_flux_v0.9.0.safetensors' not in []
If you want to bypass the Florence2 so you can use your prompt just bypass only The Florence2 node and then add text prompt encoder to replace it so you can use your prompt instead.
do you not find that using PulID the face are always facing at the same point as the reference image? and the image seems not that realistic in comparison to using reactor
yes but you need to add emotion to the prompt to make the image change it's reference point, for example you can add smile, angry, wink and so on. this will make sure the image although maintain resemblance, but will change emotion.
if you have pinokio already installed on Mac just follow the same steps however use terminal to locate the paths CD into the directory for example, you use: CD /Users/YourMacUsername/pinokio/api/comfyui.git/app/custom_nodes/
follow exactly as shown in the video after downloading the file unzip it and make sure the content is placed to the path: C:\pinokio\api\comfyui.git\app\models\insightface\models\antelopev2
Awesome tutorial but I am stuck on Load PulID FLux Mod Node , it does not show any models. I am assuming it is looking for pulid_flux_v0.9.0.safetensors. What folder should it be in for this node to see it please?
you need to create a sub-folder inside the model folder and name it pulid and place the model inside it as shown in this tutorial please watch: ua-cam.com/video/xUduNl7-pE0/v-deo.html
I placed it in the folder, next you say to paste the instalation code or path using the cmd, enter, then paste where can I get the path or code can you post it or a link thanks
Thanks. Got it to work but the output doesn't really match her face using the provided workflow. I used images very close to the example above. Any adjustments to be made to the parameters if this is happening? I found mine worked better if I swapped the images compared to the video. Can you post the Midjourney prompt so we can follow along? Thanks.
you need to change the checkpoint to the flux model you are using, if you are using a GGUF flux version change the model node to gguf unet loader checkpoint. that should fix it.
Thanks for the tutorial. Got everything to work except Insightface. I always get an "Path not Found" error as i am trying to install it via the command termina
check to see your path and apply appropriately mine was E: that's why the code I gave you was E: check what is yours and edit the code, hopefully that will work.
@@AiMotionStudio thanks! yeah there is always a typo somewhere i guess^^. now i managed to install everything but i still get a "PulidFluxInsightFaceLoader "😔 any ideas about that?
@PunxTV123 actually yeah. The Problem was during unzipping the Antelopefolder gets unzipped into a second Antelope Folder. Thats why Comfy couldn‘t locate the path correctly
There are some files that aren't installed through this procedure but finding the files on huggingface according to screens in this video got this working. None of the results are looking anything like my reference image but it's find playing around with it. Thanks again for this tutorial.
if you are using pinokio just check the path file location on the video and copy the code in the description to install the insight face and then make sure you change the drive in the code as mine is E: drive yours maybe C: and it should be straight forward.
same here: Microsoft Windows [Version 10.0.19045.5011] (c) Microsoft Corporation. All rights reserved. D:\pinokio\api\comfy.git\app>D:\pinokio\api\comfyui.git\app\env\Scripts\python.exe -s -m pip install -r requirements.txt onnxruntime The system cannot find the path specified. D:\pinokio\api\comfy.git\app>D:\pinokio\api\comfyui.git\app\env\Scripts\python.exe -m pip install D:\pinokio\api\comfyui.git\app\insightface-0.7.3-cp310-cp310-win_amd64.whl onnxruntime The system cannot find the path specified. D:\pinokio\api\comfy.git\app>D:\pinokio\api\comfyui.git\app\env\Scripts\python.exe -m pip install facexlib onnxruntime The system cannot find the path specified. D:\pinokio\api\comfy.git\app>
everything was working fine, untill the end part ERROR:- " SamplerCustomAdvanced expected scalar type Half but found BFloat16 " . can you help me please. i tried googling but its more of technical , cant seems to understand.
make sure you update your comfyui to the latest version 2.0 and follow the steps in the video if you still run into an error, you may need to install and update the pip torch as well, error using Pulid is common I got mine working after updating the comfyui to 2.0.
@@AiMotionStudio made it work. i believe it was problem with either insight face or facexlib. i have installed both of them again. so am not sure which one showed me error.
We were able to fix this error using this: github.com/comfyanonymous/ComfyUI/issues/5601 just go to your E:\pinokio\api\comfyui.git\app\comfy\ldm\flux folder and edit the model file with notepad+ and search for "out = self.forward_orig" line 184 and remove ", transformer_options" at the end of that line and save changes this will fix this errors
Hi, good I was going super well following the tutorial until minute 3:20 where I copied the command and I get this error I figured superabsurd rookie error, so I thank you for taking the time to help me out \pinokio.git.git.scripts.exe -m pip install facexlib onnxruntime The system cannot find the specified path.
Make sure 1- ComfyUI is uptodate. 2 - Goto the "...ComfyUI\custom_nodes\ComfyUI-PuLID-Flux \" Directory. 3- On the address bar type "CMD" to go into Command prompt. (Black screen with current directory) 4 - On the prompt type "pip install -r requirements.txt" Make sure the python is installed. 5- After few minutes depending on the speed of the internet it will download everything and install the dependencies and create directories in COmfyUI. 6 - Type "pip list" and check the list if the items are listed in requirements.list "facexlib, insightface, onnxruntime, onnxruntime-gpu, ftfy, timm"
I was installing insightface in ConfyUI and after the installation I encountered this error. "KSampler forward_orig() takes from 7 to 9 positional arguments but 10 were given" Has anyone encountered something similar, if you can provide me with a solution I would really appreciate it!
most people find it working after they installed the latest update version of comfyui 2.0. i think the problem is with the old comfyui had not fixed the torch pip errors that usually comes with using comfyui. Try to check on the video again, follow all the steps and instal the latest Comfyui. hopefully it will fix the issues. Let me know if you have any other questions.
We were able to fix this error using this: github.com/comfyanonymous/ComfyUI/issues/5601 just go to your E:\pinokio\api\comfyui.git\app\comfy\ldm\flux folder and edit the model file with notepad+ and search for "out = self.forward_orig" line 184 and remove ", transformer_options" at the end of that line and save changes this will fix this errors
for some reason, after installing all requirements the advance sampler reach 70% then output an error Exception during processing !!! expected scalar type Half but found BFloat16
The PuLID nodes refuse to install (IMPORT FAILED) in the Manager. I followed all the steps (changing a few things because I'm using ComfyUI Portable). Another ComfyUI FAIL. You should be able to just open a workflow, click update and it should update everything it needs to make the workflow work. Image if you had to do all this to install a windows program. Windows would of never of succeeded.
Pulid is really known to have issues installing, if you are using comfyui portable I think it will not work, I myself tried installing it via Pinokio several times, it only worked when I changed the comfyui to the newest version 2.0 and then installed all the dependencies as shown in the video, a lot of people was able to install not via Pinokio but I was able to do it with Pinokio following all the steps in the video. I will suggest that you don't delete the comfyui potable but install a new version of it separately into another folder and then try it again.
make sure the files of the folder D:\pinokio\api\comfyui.git\app\models\insightface\models\antelopev2 are in the root of the folder en not in a subfolder. That solved it for me.
you can add emotion into the prompt like saying the subject to smile, laugh or any emotion you like, make sure you bypass the florence2 node and add prompt manually to use emotion into the prompt.
Thanks a lot, i was able thru your step by step guide gets reactor faceswap running.
You are welcome! Glad to know
Thanks for the tutorial, I was able to set up everything accordingly. But I am getting this error at 73% SamplerCustomAdvanced expected scalar type Half but found BFloat16. Please help :)
Try to update the comfyUI to the new 2.0 version this should solve the errors
@@AiMotionStudio I redownloaded ComfyUI, and re-did the whole process. It is Comfy 2.0, still same error :(
Maybe it's the lack of vram? I have a 2080 Super. I tried using GGUF models as well.
We were able to fix this error using this: github.com/comfyanonymous/ComfyUI/issues/5601 just go to your E:\pinokio\api\comfyui.git\app\comfy\ldm\flux folder and edit the model file with notepad+ and search for "out = self.forward_orig" line 184 and remove ", transformer_options" at the end of that line and save changes this will fix this errors
system cannot find the path specified at the last part where we install requirements.txt cant find the solution
make sure your path is correct dont use mine, Mine is drive E: maybe yours will be C: please check to make sure!
@@AiMotionStudio there isnt python.exe in scripts should I have it ?
@@AiMotionStudio
after having some problems I reinstalled python and comfy I have to install pulid rn but when I try to install for example C:\Users\user\Desktop\ComfyUI_windows_portable\python_embeded\Scripts\python.exe -m pip install C:\Users\user\Desktop\ComfyUI_windows_portable\ComfyUI\insightface-0.7.3-cp312-cp312-win_amd64.whl onnxruntime this insight face I get this C:\Users\user\Desktop\ComfyUI_windows_portable\python_embeded\Scripts\python.exe' is not recognized as an internal or external command,operable program or batch file.
same for requirements.txt as well
they key is to build the insightface wheel manually to get it to work
Exactly!
Hello, I hope you can help me because I get an error when I start CMD. I get "git" which is not recognized as an internal or external command, program or executable batch file. I hope you can help me. I have the latest version of comfyui installed on pinokio.
make sure you use CMD into the path specified on the tutorial, if your path is not correct you will get this error.
Hello! Tell me how to fix it?
SamplerCustomAdvanced
forward_orig() takes from 7 to 9 positional arguments but 10 were given
most people find it working after they installed the latest version of comfyui 2.0. i think the problem is with the old comfyui had not fixed the torch pip errors that usually comes with using comfyui. Try to check on the video again, follow all the steps and instal the latest Comfyui. hopefully it will fix the issues. Let me know if you have any other questions.
This is a problem with comfyui. If you revert to the old version, the problem will be gone. Go to the comfyui directory and run "git reset --hard cc9cf6d1bd957d764ad418258b61d7e08187573b"
@@murattuanaahmet Hello! Thanks for the recommendation, in my case the problem was in the python version, after updating it everything worked, but I couldn't achieve such similarity as the video, in principle it works at the level of Stable Diffusion Insta Swap or Reactor.
We were able to fix this error using this: github.com/comfyanonymous/ComfyUI/issues/5601 just go to your E:\pinokio\api\comfyui.git\app\comfy\ldm\flux folder and edit the model file with notepad+ and search for "out = self.forward_orig" line 184 and remove ", transformer_options" at the end of that line and save changes this will fix this errors
👍👍👍maravilha....
I could not achieve facial consistency in my experiments. I think the resolution of the reference image I use has an effect on this. Can you give information about the size of the reference images you use?
The size of the reference image I used was 1778x2667 but I think it does not matter the size, as long as the face is detailed enough.
What's the difference between reactor face swap?
Flux Pulid is a lora replacement, so you don't have to train lora for hours, with pulid you can instantly generate a consistent face with just one reference image.
@@AiMotionStudioyou didn't answer the question...
@@lordmo3416 face swap does not use a flux model to re-generate the image, while pulid uses flux therefore makes the image quality generation high.
@@AiMotionStudioyou realize there is a ComfyUI Reactor Node available for Flux, right?
@@eccentricworx Reactor uses its own model to faceswap after the generation, but PuLID is a controlnet, I think. Hope that helps.
could you make step by step how u did your elevenlabs train ?
i already did it, here is the video tutorial: ua-cam.com/video/KtYooOgW7t0/v-deo.html
Thank you!
You're welcome!
I have downloaded the pulid model safetensors and placed it in the Pulid folder. But why does it always stop at the flux model Puled node?
Failed to validate the prompt for output 9:
* PulidFluxModelLoader 99:
- Value not in list: pulid_file: 'pulid_flux_v0.9.0.safetensors' not in []
you have to update ComfyUI to Version v0.2.6 and this will fix all issues.
I don't know which windows to bypass, since the quality is to low to read the captions. I tried to figure it out, but then I get a lot of errors.
If you want to bypass the Florence2 so you can use your prompt just bypass only The Florence2 node and then add text prompt encoder to replace it so you can use your prompt instead.
This is good but I would love to add the loraturbo for speed, can you tell me whre can I add loras to this workflow?
actaully this workflow does not need lora, you can however use lora after genration during upscalling the images that is what i need.
do you not find that using PulID the face are always facing at the same point as the reference image? and the image seems not that realistic in comparison to using reactor
yes but you need to add emotion to the prompt to make the image change it's reference point, for example you can add smile, angry, wink and so on. this will make sure the image although maintain resemblance, but will change emotion.
@@AiMotionStudio hmm will try but how will you change where the character is facing though?
Hey, thanks for sharing! How do I install all this on MAC?
if you have pinokio already installed on Mac just follow the same steps however use terminal to locate the paths CD into the directory for example, you use: CD /Users/YourMacUsername/pinokio/api/comfyui.git/app/custom_nodes/
i am confused with the installation of antelopeV2, in the models folder i dont have insightface folder, what to do ?
follow exactly as shown in the video after downloading the file unzip it and make sure the content is placed to the path: C:\pinokio\api\comfyui.git\app\models\insightface\models\antelopev2
same issue, did you resolve it?
Awesome tutorial but I am stuck on Load PulID FLux Mod Node , it does not show any models. I am assuming it is looking for pulid_flux_v0.9.0.safetensors. What folder should it be in for this node to see it please?
you need to create a sub-folder inside the model folder and name it pulid and place the model inside it as shown in this tutorial please watch: ua-cam.com/video/xUduNl7-pE0/v-deo.html
I cannot find the instalation code that goes into app folder where is it??
check for folder that has both comfyui.prev and comfyui.prev2 file thats the file you need to place the file into
I'm also stuck with this.
@@WD_MyImage what is yhe instalation code that I have to use with cmd command ,I cant find the code to paste it and hit enter
I placed it in the folder, next you say to paste the instalation code or path using the cmd, enter, then paste where can I get the path or code can you post it or a link thanks
Hi, which is the correct eva clip file? There are a lot of versions. Thanks.
the one with the Zip folder includes all the files so just doenload that and unzip it into the AntelopV2 folder
Thanks. Got it to work but the output doesn't really match her face using the provided workflow. I used images very close to the example above. Any adjustments to be made to the parameters if this is happening? I found mine worked better if I swapped the images compared to the video. Can you post the Midjourney prompt so we can follow along? Thanks.
Output images are blurry. I increased steps but didn't help
Use a lower denoise value
hello, i have this error : - Value not in list: unet_name: 'flux1-dev.sft' not in []. idk where to find this .sft
you need to change the checkpoint to the flux model you are using, if you are using a GGUF flux version change the model node to gguf unet loader checkpoint. that should fix it.
@@AiMotionStudio i have the same error, i put flux-dev Q4 GGUF version at unet folder. and it says it can't find it. i used Load diffusion model not.
Thanks for the tutorial. Got everything to work except Insightface. I always get an "Path not Found" error as i am trying to install it via the command termina
check to see your path and apply appropriately mine was E: that's why the code I gave you was E: check what is yours and edit the code, hopefully that will work.
@@AiMotionStudio thanks! yeah there is always a typo somewhere i guess^^. now i managed to install everything but i still get a "PulidFluxInsightFaceLoader
"😔 any ideas about that?
@@StargazerFilms87 You got a lot farther than me.
@@StargazerFilms87 same, did you fix it? got error Missing Node Types
ApplyPulidFlux
PulidFluxEvaClipLoader
PulidFluxModelLoader
PulidFluxInsightFaceLoader
@PunxTV123 actually yeah. The Problem was during unzipping the Antelopefolder gets unzipped into a second Antelope Folder. Thats why Comfy couldn‘t locate the path correctly
Nodes for "Load Diffusion Model", "DualCLIPLoader" and "Load VAE" are framed in red and no output.... Node manager doesn't show anything as missing.
There are some files that aren't installed through this procedure but finding the files on huggingface according to screens in this video got this working. None of the results are looking anything like my reference image but it's find playing around with it. Thanks again for this tutorial.
you have to update ComfyUI to Version v0.2.6 and this will fix all issues.
the insight face part is confusing
if you are using pinokio just check the path file location on the video and copy the code in the description to install the insight face and then make sure you change the drive in the code as mine is E: drive yours maybe C: and it should be straight forward.
same here: Microsoft Windows [Version 10.0.19045.5011]
(c) Microsoft Corporation. All rights reserved.
D:\pinokio\api\comfy.git\app>D:\pinokio\api\comfyui.git\app\env\Scripts\python.exe -s -m pip install -r requirements.txt onnxruntime
The system cannot find the path specified.
D:\pinokio\api\comfy.git\app>D:\pinokio\api\comfyui.git\app\env\Scripts\python.exe -m pip install D:\pinokio\api\comfyui.git\app\insightface-0.7.3-cp310-cp310-win_amd64.whl onnxruntime
The system cannot find the path specified.
D:\pinokio\api\comfy.git\app>D:\pinokio\api\comfyui.git\app\env\Scripts\python.exe -m pip install facexlib onnxruntime
The system cannot find the path specified.
D:\pinokio\api\comfy.git\app>
everything was working fine, untill the end part ERROR:- " SamplerCustomAdvanced
expected scalar type Half but found BFloat16 " . can you help me please. i tried googling but its more of technical , cant seems to understand.
make sure you update your comfyui to the latest version 2.0 and follow the steps in the video if you still run into an error, you may need to install and update the pip torch as well, error using Pulid is common I got mine working after updating the comfyui to 2.0.
@@AiMotionStudio made it work. i believe it was problem with either insight face or facexlib. i have installed both of them again. so am not sure which one showed me error.
We were able to fix this error using this: github.com/comfyanonymous/ComfyUI/issues/5601 just go to your E:\pinokio\api\comfyui.git\app\comfy\ldm\flux folder and edit the model file with notepad+ and search for "out = self.forward_orig" line 184 and remove ", transformer_options" at the end of that line and save changes this will fix this errors
Stumbles on node "Load InsightFace (PuLID FLUX)" PulidInsightFaceLoader Error
you have to update ComfyUI to Version v0.2.6 and this will fix all issues.
Hello, can we do this face swap with my 6gb vram graphics card? If I can, can you give me the workflow fee?
Yes I believe you can, however it maybe slow to generate, for the workflow it’s free, check the video description for the link to the workflow
I tried following your tutorial with Zendaya. Why is the output not looking like her at all?
Try to increase the denoise to get higher resemblance
@@AiMotionStudio Under Basic Scheduler? It is at max @ 1.
Hi, good I was going super well following the tutorial until minute 3:20 where I copied the command and I get this error I figured superabsurd rookie error, so I thank you for taking the time to help me out
\pinokio.git.git.scripts.exe -m pip install facexlib onnxruntime
The system cannot find the specified path.
Make sure
1- ComfyUI is uptodate.
2 - Goto the "...ComfyUI\custom_nodes\ComfyUI-PuLID-Flux \" Directory.
3- On the address bar type "CMD" to go into Command prompt. (Black screen with current directory)
4 - On the prompt type "pip install -r requirements.txt" Make sure the python is installed.
5- After few minutes depending on the speed of the internet it will download everything and install the dependencies and create directories in COmfyUI.
6 - Type "pip list" and check the list if the items are listed in requirements.list
"facexlib, insightface, onnxruntime, onnxruntime-gpu, ftfy, timm"
I was installing insightface in ConfyUI and after the installation I encountered this error.
"KSampler forward_orig() takes from 7 to 9 positional arguments but 10 were given"
Has anyone encountered something similar, if you can provide me with a solution I would really appreciate it!
most people find it working after they installed the latest update version of comfyui 2.0. i think the problem is with the old comfyui had not fixed the torch pip errors that usually comes with using comfyui. Try to check on the video again, follow all the steps and instal the latest Comfyui. hopefully it will fix the issues. Let me know if you have any other questions.
We were able to fix this error using this: github.com/comfyanonymous/ComfyUI/issues/5601 just go to your E:\pinokio\api\comfyui.git\app\comfy\ldm\flux folder and edit the model file with notepad+ and search for "out = self.forward_orig" line 184 and remove ", transformer_options" at the end of that line and save changes this will fix this errors
for some reason, after installing all requirements the advance sampler reach 70% then output an error Exception during processing !!! expected scalar type Half but found BFloat16
Update comfyUI to the newest version 2.0 then update all nodes and try it again.
@@AiMotionStudio it's already updated to latest version, both nodes and comfyui
@@AiMotionStudio i have already updated everything, both comfyui and all nodes, but the problem remain for some reasons
The PuLID nodes refuse to install (IMPORT FAILED) in the Manager. I followed all the steps (changing a few things because I'm using ComfyUI Portable). Another ComfyUI FAIL.
You should be able to just open a workflow, click update and it should update everything it needs to make the workflow work.
Image if you had to do all this to install a windows program. Windows would of never of succeeded.
Pulid is really known to have issues installing, if you are using comfyui portable I think it will not work, I myself tried installing it via Pinokio several times, it only worked when I changed the comfyui to the newest version 2.0 and then installed all the dependencies as shown in the video, a lot of people was able to install not via Pinokio but I was able to do it with Pinokio following all the steps in the video. I will suggest that you don't delete the comfyui potable but install a new version of it separately into another folder and then try it again.
@@AiMotionStudio Thanks. Maybe I will try again.
You can't make her do different emotions though, but lora can.
actually you can just add in the emotion in the prompt and it will be applied.
Error: PulidFluxInsightFaceLoader
# ComfyUI Error Report
## Error Details
- **Node Type:** PulidFluxInsightFaceLoader
- **Exception Type:** AssertionError
- **Exception Message:**
## Stack Trace
```
you have to update ComfyUI to Version v0.2.6 and this will fix all issues.
@AiMotionStudio I updated comfy yesterday in the manager but still doesn't work, is there another way to update it?
make sure the files of the folder D:\pinokio\api\comfyui.git\app\models\insightface\models\antelopev2 are in the root of the folder en not in a subfolder. That solved it for me.
🎉🎉🎉🎉
at 3:24 paste what installation code?
E:\pinokio\api\comfyui.git\app\env\Scripts\python.exe -m pip install E:\pinokio\api\comfyui.git\app\insightface-0.7.3-cp310-cp310-win_amd64.whl onnxruntime
E:\pinokio\api\comfyui.git\app\env\Scripts\python.exe -m pip install E:\pinokio\api\comfyui.git\app\insightface-0.7.3-cp310-cp310-win_amd64.whl onnxruntime
where did she got this code? stuck
not using pinokio
if you are not using pinokio just navigate to the same folder with similar content comfyui.prev and comfyui.prev2
@@AiMotionStudio I figured it out thanks
emotion seem all the same
you can add emotion into the prompt like saying the subject to smile, laugh or any emotion you like, make sure you bypass the florence2 node and add prompt manually to use emotion into the prompt.
Hi! How do I change the prompt from "U-NAI Get Text"? Its greyed out and wont even let me delete the prompt loaded there?
you need to bypass the florence2 node, U-Nai Get, and add CLIP Text Encode (Positive Prompt) and link it to FluxGuidance conditioning.