![[ADVANCED WORKFLOWS] Create CONSISTENT CHARACTERS for your projects with FLUX! + UPDATE](https://img5.xaiju.com/storage/1/is/qf/d38796-019e8569-d9fe-7aa6-b2ec-440946f8b5ee.png)
![[ADVANCED WORKFLOWS] Create CONSISTENT CHARACTERS for your projects with FLUX! + UPDATE](https://img5.xaiju.com/storage/2/sq/fo/d38796-019e8569-dabd-78cf-9829-13095b081416.jpg)
[ADVANCED WORKFLOWS] Create CONSISTENT CHARACTERS for your projects with FLUX! + UPDATE
Added 2024-10-10 15:13:16 +0000 UTCThank you so much for supporting the channel and my work! ❤️
Be sure to check out our community Discord and let me know what you want to see next!
Below you can download:
Sample FLUX Training Datasets
The Flux Loras I trained with these datasets
The character sheets for creating the datasets (including metadata: Just drag and drop them into ComfyUI to start the dataset creation workflow, including the prompt)
The advanced workflow for FLUX
The advanced workflow for SDXL
Thanks again for making these videos possible. I hope you can create some amazing things with them. Be sure to share these results in our Discord :)
UPDATE
I just uploaded a new Version with a new Control net Implementation that should fix the errors some of you have been experiencing. "241027_MICKMUMPITZ_CHARACTER_SHEET_V05_FLUX_ADV.json"
Comments
The nodes used in the workflow wont update I have tried to install them and it keeps saying there are conflicting nodes.
Nicholas Boyer
2025-03-30 13:34:06 +0000 UTCNone of the nodes work for some reason keep getting errors even though I installed everything in the walk through for flux. I put the appropriate file in the appropriate folder. Restarted/refreshed. literally like every node is missing the files.
Nicholas Boyer
2025-03-30 13:25:57 +0000 UTChello, im running to this when queue it, i dunno where to put bbox/face_yolov8m.pt in which location, can someone help me out? " Prompt outputs failed validation UltralyticsDetectorProvider: - Value not in list: model_name: 'bbox/face_yolov8m.pt' not in [] UltimateSDUpscale: - Value not in list: force_uniform_tiles: 'True' not in ['enable', 'disable'] UpscaleModelLoader: - Value not in list: model_name: '4x-ClearRealityV1.pth' not in [] CheckpointLoaderSimple: - Value not in list: ckpt_name: 'wildcardxXLTURBO_wildcardxXLTURBOV10.safetensors' not in ['hassakuXLIllustrious_v13StyleA.safetensors', 'style_handsomemale.safetensors'] ControlNetLoader: - Value not in list: control_net_name: 'OpenPoseXL2.safetensors' not in [] UltimateSDUpscale: - Value not in list: force_uniform_tiles: 'True' not in ['enable', 'disable'] ControlNetLoader: - Value not in list: control_net_name: 'sdxl\mistoLine_rank256.safetensors' not in []"
dat nguyen
2025-02-28 10:02:05 +0000 UTCTo load the ControlNet model correctly (which needs to be compatible with your base model), you may need to rename the model file. According to official documentation, you should rename the file from: diffusion_pytorch_model.safetensors to instantx_flux_canny.safetensors This ensures proper recognition and compatibility with the base Stable Diffusion model you're using. Always verify that the ControlNet model version matches your base model architecture (e.g., SD1.5/SDXL-compatible). For English users: When loading ControlNet models, ensure filename alignment. Rename diffusion_pytorch_model.safetensors → instantx_flux_canny.safetensors as per official specifications for base model compatibility.
ZHAO CHENG
2025-02-11 17:13:05 +0000 UTCHave you found a solution on this?
Maria Bartzoka
2025-02-11 16:23:23 +0000 UTCFluxParams.__init__() missing 2 required positional arguments: 'out_channels' and 'patch_size' Can you advise me on the next steps?
ZHAO CHENG
2025-02-11 15:42:11 +0000 UTCSame Problem here. mat1 and mat2 shapes cannot be multiplied (1x1280 and 2816x1280) How can i fix it?
Maria Bartzoka
2025-02-11 15:36:31 +0000 UTCSamplerCustomAdvanced mat1 and mat2 shapes cannot be multiplied (1x768 and 2816x1280) Can you advise me on the next steps?
ZHAO CHENG
2025-02-10 21:13:04 +0000 UTCFor some reason the SAVE POSES group isn't receiving the images from the face detailer pipe. This causes the rest of the workflow to fail. Has anyone else had this issue?
Squint Dev
2025-02-10 20:00:51 +0000 UTCOn the second step. Where the face detailer is, the right soft image breaks the face, especially in anime characters. As if the modified face is superimposed on the original and also flattened. Changing the face detailer settings does not give a result. If anyone has encountered this, please help, I added an image upload node and send the corrected face in Photoshop via workflow, this is far from a working workflow and automation.
Сергей Щерба
2025-02-09 07:20:09 +0000 UTCsee Amber's post below - that node is deprecated. Replace with native ComfyUI nodes (add connect Load ControlNet Model to SetUnionControlNetType and connect to node ID333)
Paul H
2025-01-28 11:51:51 +0000 UTCme too
inverse
2025-01-24 07:34:32 +0000 UTCgot prompt invalid prompt: {'type': 'invalid_prompt', 'message': 'Cannot execute because a node is missing the class_type property.', 'details': "Node ID '#335'", 'extra_info': {}} anyone having troubles with imagetobatchlist+ ??
inverse
2025-01-24 02:48:47 +0000 UTCHello ! , was trying : 241007_MICKMUMPITZ_CHARACTER_SHEET_V02_SDXL_ADV some crazy error message ;))) if you happen to understand there meanings ;)) groovy !!! here they are : No operator found for `memory_efficient_attention_forward` with inputs: query : shape=(2, 4096, 10, 64) (torch.float16) key : shape=(2, 4096, 10, 64) (torch.float16) value : shape=(2, 4096, 10, 64) (torch.float16) attn_bias : p : 0.0 `fa3F@0.0.0` is not supported because: xFormers wasn't build with CUDA support requires device with capability > (9, 0) but your GPU has capability (8, 6) (too old) operator wasn't built - see `python -m xformers.info` for more info `fa2F@0.0.0` is not supported because: xFormers wasn't build with CUDA support operator wasn't built - see `python -m xformers.info` for more info `cutlassF-pt` is not supported because: xFormers wasn't build with CUDA support got RTX A5000 24gigs of ram and latest win 11 pro + nvidia drivers up to date... and still . out of the game ?
yannosse
2025-01-21 14:54:20 +0000 UTCI am having the same issue. No upscaling of emotions. Were you able to fix it Rahul?
Jorge Sagasti
2025-01-20 16:22:27 +0000 UTCFor 2410127 try the link further below. I just downloaded all files successfully to a fresh install of ComfyUI.
Soul Merge
2025-01-08 06:50:02 +0000 UTCExpired URL
Goqor Grigoryan
2025-01-07 12:05:10 +0000 UTC241027_MICKMUMPITZ_CHARACTER_SHEET_V05_FLUX_ADV.json is not working at last step where emotions are upscaling how to fix that
Rahul Gupta
2024-12-17 13:25:30 +0000 UTCAlso in Flux V05 in the first stage you have the SetUnionControlNetType node set to to auto !!! Which means it will start from the beginning every time you want to make a settings change in a later stage. Even on 4090 it takes a long time, change the negative prompt in the last upscale stage and..... start all the way from the beginning again lol. So set it to something not auto!! Actually it's better to just remove the type node as they can all give weird results, I guess that's the reason for setting it to auto, but then the problem above. Amazing workflow though now I've done a few.
Amber View
2024-12-10 11:29:08 +0000 UTCBy the way, the InstantX Flux Union ControlNet Loader node used at the end of the Flux V05 workflow does not work in the latest ComfyUI, and it is a deprecated node. Here is the guys GitHub where he gives a link to an alternative. https://github.com/EeroHeikkinen/ComfyUI-eesahesNodes
Amber View
2024-12-10 04:21:03 +0000 UTCI answered a question to someone below and I think it needs to go at the top well! ...Comfyui is not easy to get working with a lot of different 3rd party installed nodes for good workflows like this one. But it is quite ok when you learn how to install nodes and fix errors. Look at pixorama on YouTube he does a lot of node fixing in his videos. Use an LLM and paste errors into it. Go to your Comfyui custom nodes folder, look at the nodes you have in there, each one has a GitHub page that shows install requirements and the issues section has fixes. Nodes can conflict with each other, if you are having big problems move all nodes from custom folder to desktop and install and check 1 by 1. Comfyui has a button that goes to the github errors page for the node when it errors sometimes. Lastly your system python version needs to be compatible and you sometimes need to install the requirements.txt in the custom nodes folder into the python_embedded folder in Comfyui folder rather than into your system python. An LLM, Chat Gpt etc will tell you how to do that, just paste errors from cmd window into it, and the Github pages for each node, that is how to fix everything Comfyui! Have a nice day.
Amber View
2024-12-09 22:41:28 +0000 UTCDid you get if fixed? Comfyui is not easy to get working with a lot of different 3rd party installed nodes for good workflows like this one. But it is quite ok when you learn how to install nodes and fix errors. Look at pixorama on YouTube he does a lot of node fixing in his videos. Use an LLM and paste errors into it. Go to your Comfyui custom nodes folder, look at the nodes you have in there, each one has a GitHub page that shows install requirements. Comfyui has a button that goes to the github errors page when it errors usually. Lastly your system python version needs to be compatible and you sometimes need to install the requirements.txt in the custom nodes folder into the python_embedded folder in Comfyui folder. An LLM, Chat Gpt etc will tell you how to do that, just paste errors into it, and the Github pages for each node, that is how to fix everything. Have a nice day.
Amber View
2024-12-09 22:27:43 +0000 UTCI'm getting this message that is missing InstantX Flux Union ControlNet Loader Could you please help me to install it? I have already download it, and it came with this name: diffusion_pytorch_model.safetensors Should I change the name for instantx_flux_union.safetensors ??
Fabio Garcia
2024-12-08 02:21:35 +0000 UTCWhich folder should I put it in?
Fabio Garcia
2024-12-07 20:08:39 +0000 UTCIs it possible to use an image of character that I already have instead using prompt?
Fabio Garcia
2024-12-07 19:52:30 +0000 UTCsame issue here
Nathan Duncan
2024-12-04 05:05:45 +0000 UTC241027_ you sure its not 241127 ?
rubz
2024-11-27 00:16:41 +0000 UTCHI!, what does this issue mean? InstantX Flux Union ControlNet Loader FluxParams.__init__() missing 2 required positional arguments: 'out_channels' and 'patch_size'
luis villalba
2024-11-25 00:40:33 +0000 UTCI've got it working recently, about 3 days ago after stepping away for a bit. I did use chatGPT in conjunction with the error logs ComfyUI generated to help me nail down some problems. Most of the problems I had were putting things in the proper folders.
Benjamin Lebron
2024-11-23 01:32:03 +0000 UTCDownloaded this controlnet: https://huggingface.co/InstantX/FLUX.1-dev-Controlnet-Union/tree/main Now I get an image, but it's only a single side profile face image.
Andrew Taylor
2024-11-22 20:03:45 +0000 UTCHas anyone got this working? I haven't had any issue with errors, but all it generates is a copy of the pose png. Can't post screenshots here :(
Andrew Taylor
2024-11-22 19:38:38 +0000 UTCAnyone got this workflow working?
Zulfariz Abd Majid
2024-11-17 15:07:00 +0000 UTCHi, I'm getting an error, my all "Apply controlnet nodes are in red color which is showing controlnet dot in a red circle. can anyone help me?
Wasay ali
2024-11-16 07:45:35 +0000 UTCHi, there is no image come up when I using FLUX. The SAVE IMAGE node have red line around it (I guess that is the culprit). Please help how to solve this problem?
Zulfariz Abd Majid
2024-11-14 09:21:14 +0000 UTCI'm not sure why his safetensor files are named differently. However, this is the correct file.
Kelevra
2024-11-05 14:16:04 +0000 UTChttps://huggingface.co/InstantX/FLUX.1-dev-Controlnet-Union/blob/main/diffusion_pytorch_model.safetensors
Kelevra
2024-11-05 13:11:14 +0000 UTCWhere can I find the "InstantX_flux.safetensor" file to download? I was not able to located it anywhere online... Thanks!
Clemens Simlinger
2024-11-05 11:59:28 +0000 UTCI hope I'm not breaking any rules by posting a link to another Patreon creator's page. My sole intention is to help others that are having the same problem. I installed a fresh copy of ComfyUI using his main installer on a separate drive. https://www.patreon.com/posts/115233636. I then ran the INSIGHTFACE_AUTO_INSTALL.bat. I also needed to install a few missing safe-tensor files. https://huggingface.co/mcmonkey/google_t5-v1_1-xxl_encoderonly/tree/main https://huggingface.co/zer0int/CLIP-GmP-ViT-L-14/blob/main/ViT-L-14-TEXT-detail-improved-hiT-GmP-TE-only-HF.safetensors https://huggingface.co/InstantX/FLUX.1-dev-Controlnet-Union/blob/main/diffusion_pytorch_model.safetensors This fixed the problem for me.
Kelevra
2024-11-05 02:09:28 +0000 UTCI'm currently experiencing the same problem as Hipflow.
Kelevra
2024-11-04 14:42:21 +0000 UTCi ve problem some missing node : pulidFluxEcacliploader, pulidfluxinsightfaceloader,applypulidflux, pulidfluxmodel loader
HipFlow
2024-11-03 15:26:24 +0000 UTCI have found the reason why workflows are not working. ThinkDiffusion does not support ComfyUI Impact Pack nodes. Maybe it`s not a big deal when you know how to replace those nodes with different ones. But I don't) Could you help?
Vitalii Mykhailyshyn
2024-11-01 12:08:58 +0000 UTCDefinetly this would be amazing, like a description image after input a photo, or add the same prompt and seed,. size with x model, and later get the photo album
Ebba Vei
2024-11-01 08:36:09 +0000 UTCHey, does anyone using ThinkDiffusion and workflow works for him?
Vitalii Mykhailyshyn
2024-11-01 00:37:37 +0000 UTCIm having the same issue as Mr. Vitalii
Benjamin Lebron
2024-10-31 21:06:21 +0000 UTCThank you, I'll keep a lookout. I'm using the ComfyUI Windows Portable version with the Comfy Ui Manager. It just won't install two custom nodes ComfyUI_Impact or something like that (I don't have it in front of me atm)
Benjamin Lebron
2024-10-31 21:05:31 +0000 UTCHi! Is there any way to use this workflow with a reference image, for example, If I created a character in Leonardo AI and I want the same character with this workflow, can I do that?
Marco Ramley
2024-10-31 19:42:59 +0000 UTCI`m using ComfyUI with ThinkDiffusion. Could you try to go through all the processes there? I have tried all workflows. The result is - this list of nodes just can`t to install. UI Manager installed all nodes + all updated, but this list is not changing: When loading the graph, the following node types were not found: CoreMLDetailerHookProvider ToDetailerPipe ToBasicPipe UltralyticsDetectorProvider FaceDetailerPipe FromBasicPipe_v2 Nodes that have failed to load will show as red on the graph. So basically some part of bottom nodes are red and that's all.
Vitalii Mykhailyshyn
2024-10-31 17:11:28 +0000 UTCI'm sorry about that. I am currently recording a new tutorial with the updated version that shows the full installation process step by step. I hope that helps. Are you using ComfyUI with ThinkDiffusion?
Mick Mahler
2024-10-31 15:32:45 +0000 UTCWould anyone mind sharing their files, I cant get the thing to run, keep getting errors with ComfyUI_impact and another node. been 2 weeks of troubleshooting and reading documentation :-(
Benjamin Lebron
2024-10-29 20:13:20 +0000 UTCHow do I combined your flux lora workflow and the Anime Position work flow? I want to take my poses and add my characters
Tony Gonzales
2024-10-29 04:12:28 +0000 UTCOnly 4 emotions getting upscaled, how do I get rest of the poses to upscale (flux workflow)?
Len
2024-10-29 01:05:34 +0000 UTCHas anyone managed to get ComfyUI, FLUX, and LoRA working on an NVIDIA RTX L4 virtual machine on Google Cloud with Windows Server 2022, Python 3.12, CUDA 12.4, and PyTorch 2.5?
Massimo Moro
2024-10-28 13:26:07 +0000 UTCHi thanks for the amazing workflows, How can I work with Flux Lora from FluxGym with the character sheet Flux?
majdi El-Jazmawi
2024-10-27 20:30:27 +0000 UTCThe CLIP type must be set to Flux, not SDXL -- this is a bug in the workflow -- see https://github.com/comfyanonymous/ComfyUI/issues/4699#issuecomment-2350815051
Jan Minar
2024-10-27 16:43:46 +0000 UTCHi Guys! Does anyone know why changing the seed number makes the output photo blurry?
Famous People
2024-10-25 16:14:53 +0000 UTCwhat does this issue mean? mat1 and mat2 shapes cannot be multiplied (1x768 and 2816x1280)
Gerhard Bultema
2024-10-25 14:12:51 +0000 UTCthank you. I have it working now, but when i click queue prompt i'm getting: failed to validate prompt for output 87: * (prompt): - Required input is missing: images * SaveImage 87: - Required input is missing: images Output will be ignored How do i fix that output 87?
Gerhard Bultema
2024-10-25 13:32:05 +0000 UTCYou need to update and install custom nodes with Manager. To do that, go to your ConfyUI manaegr panel and click on update nodes.
Exiliem Game
2024-10-23 19:48:29 +0000 UTCi did everything in the guide, but when pasting in the character sheet i get errors i'm missing nodetypes: FromBasicPipe_v2 CoreMLDetailerHookProvider ToBasicPipe UltralyticsDetectorProvider Fast Groups Muter (rgthree) ToDetailerPipe ExpressionEditor Simple String FaceDetailerPipe ImageBatchMulti AnyLineArtPreprocessor_aux InstantX Flux Union ControlNet Loader why is this?
Gerhard Bultema
2024-10-23 17:54:52 +0000 UTCI am having issues on running this. I am using excapt same models elements from the video and it is failing. Do you know why is this error? c_net = control_net.copy().set_cond_hint(control_hint, strength, (start_percent, end_percent), vae=vae, extra_concat=extra_concat) ^^^^^^^^^^^^^^^^ AttributeError: 'NoneType' object has no attribute 'copy' 2024-10-23 10:40:59,023 - root - INFO - Prompt executed in 0.03 seconds ``` ## Attached Workflow Please make sure that workflow does not contain any sensitive information such as API keys or passwords. ``` Workflow too large. Please manually upload the workflow from local file system. ``` ## Additional Context (Please add any additional context or steps to reproduce the error here)
Exiliem Game
2024-10-23 15:42:12 +0000 UTCThis was crap. Do not buy this. Nothing but hours of wasted time and effort.
Ian Bright
2024-10-22 20:54:45 +0000 UTCalso look at the prompt clip that's going into the upscaler if it starts giving you things you don't want.
Koss Billingham
2024-10-22 10:35:42 +0000 UTCNoise Reduction solved it. it was 0.5, changed to 0.2 and it is better, now I just need to fine tune it.
Luis Oliveira
2024-10-22 09:04:54 +0000 UTCHi! Using the sdxl adv, everytime it use the emotion upscale, the colors and everything else becomes amazing, but the emotion almost disapears. A characer with open mouth and showing teeth will be upscaled wih close mouth and a almost resting posture. What can I do?
Luis Oliveira
2024-10-22 08:58:24 +0000 UTCI agree!
Luis Oliveira
2024-10-22 08:47:49 +0000 UTCIt's just as the error reads. You are missing models in your installation that the names in the UI fields are trying to call. I just posted a lengthy message up above explaining this in detail. I had to struggle though on a Mac, but I got it up and running successfully.
TJ Jones
2024-10-21 16:23:18 +0000 UTCFor those having problems, especially where you get an error to something of the sort "...safetensors not in..." This means the library you are targeting is not available. Likely you don't have it installed in the appropriate folder. For instance, the Load Diffusion Model panel, the first item is unet_name. This component is looking in your unet folder. The name on the right is the name it's looking for. The names that came in with the json workspace were for libraries I did not have. Currently I switched this to flux1-dev.safetoners, which I do have in my unet folder. Also in Load ControlNet Model panel, the control_net_name was a non-existing name for models in my controlnet folder. I had to go download a version of InstantFlux Dev Union. MAC Users. You will run into the same issue I had which is fp8 will not work with Metal (MPS). You will have to use fp16 or higher. I'm pretty new to all this, but I believe the issue here is memory. The higher floating point models require more ram. You are pretty much screwed if you don't have at least 32GB. I have 64 in a M1 Ultra Mac Studio. I have watched my RAM run up as high as 83%. Also note for Mac, DualCLIPLoader panel. You will have to load the t5xx version that is fp16 or higher. In a nutshell, I went to google with all the file names of the models I needed and it would bring me to the correct pages for download on huggingface. Not sure why some of them would not show up in huggingface's search. So just be aware. Windows Users, similar logic applies. If you are missing something and get an error that is showing this, you need to find the correct library/model, download it, and place in the appropriate folder. From there when in Comfy, make sure the field for that particular model is indeed the one you downloaded. If the names don't match, it won't work. Hope this helps... Learning all this is pretty much how I spent my Friday, and yes, I was able to get the Flux version to run on my mac with all 5 steps and produced all the images for the blonde american woman as a test run. Note, on my mac the initial character sheet took about 18 minutes. Running the remainder outputs together took 3.5 hours.
TJ Jones
2024-10-21 16:16:20 +0000 UTCdon't bother wih flux controlnet, i've tried every models possible, every settings, they all just sucks for flux. I got the same problem as you. Or by changing the settings i could get the entire sheet generated but the output quality is trash. Just don't bother using flux controlnets for now, they are not good right now. The only controllable images are in SDXL, the controlnets are good (sd1.5 are the most accurate though)
Thibaud Herbert
2024-10-20 22:55:27 +0000 UTCAs long as you take money for it PLEASE give a full instructions on how to use ADVANCED flow. Step by step. For me it's just a bunch of random files, and nothing more.
UAknight
2024-10-20 00:14:02 +0000 UTCIll trade you for the workflow. Kidding, it should be under your "Membership" tab.
R0binho0d
2024-10-19 23:55:37 +0000 UTCI keep getting picture from 3 sides instead of multiple. Is there a fix for that?
UAknight
2024-10-19 23:31:01 +0000 UTCany chance of a link to the discord?
Koss Billingham
2024-10-19 22:58:28 +0000 UTCIt's hardly stealing the thunder, if you help improve a workflow, that doesn't fully functional. Looking in the discord, there are others who keep getting those asians and plastic people. Your help would be hugely appreciated.
R0binho0d
2024-10-19 19:57:18 +0000 UTCI've given my notes to Mick, I'm not here to steal his thunder. I think an updated one is on the way anyway.
Koss Billingham
2024-10-19 19:24:47 +0000 UTC@R0binho0d - resolution is 1024 for the face crops at the end. The input resolution isn't quite as simple as I've done a bit of resizing between groups.
Koss Billingham
2024-10-19 19:05:56 +0000 UTCUnless I'm missing something, I see no mention of the files above and where they go
memyself andI
2024-10-18 20:54:56 +0000 UTC@Koss Billingham do you mind sharing your updated workflow?
R0binho0d
2024-10-18 19:25:13 +0000 UTCYour images of the blond is exactly, what I am trying to achieve :)
R0binho0d
2024-10-18 18:43:36 +0000 UTCWhat resolution are you doing? I am getting same problems as you with lots of asian and not realistic images at all.
R0binho0d
2024-10-18 18:40:10 +0000 UTC@Loxis This is what adding that LoRA did for the face at the end: https://imgur.com/a/MkMHLuW
Koss Billingham
2024-10-18 18:05:14 +0000 UTCsame
Loxis
2024-10-18 16:10:45 +0000 UTChttps://docs.google.com/document/d/1PHYMpXqfNKj9dQIMVpXAg7R4FjNFIINok09L9heQTnM/edit?tab=t.0
Koss Billingham
2024-10-18 09:14:34 +0000 UTCRight, for those having problems with the SDXL side - the main issue is the control net. Works fine on FLUX, works horrendously on SDXL. Find some pictures of people in poses that you want, use a depth map instead and then generate a bunch of individual images, in-paint the bits you don't like and then train your LoRA from there. You can take the chunks of the advanced FLUX workflow from the template and skip the first few steps, replacing them with an image loader. Bit laborious, but it works well. The FLUX workflow doesn't seem to want to generate anything approaching photo-real and keeps trying to make my characters look a bit asian for some reason, but iterating through a few different workflows to get the end result you want is where the magic happens. The principles of these workflows give you all of the tools you need to achieve it. If you want the effectiveness of the FLUX control net in SDXL, use the FLUX workflow to generate a the poses you want, then chop those up into depth maps for SDXL once you've generated the character poses. If I can do it with zero experience in AI image generation and 2-3 days of light practice, so can you. Edit 1: about to experiment with the fluxRealism LoRA at the beginning of the FLUX workflow, I'll report back with results. Edit 2: Putting the FluxRealism LoRA in at the beginning and setting the width and height to that of the control net image resolution seems to generate MUCH better looking characters if you're after realism. Edit 3: link to the FluxRealism LoRA: https://huggingface.co/XLabs-AI/flux-RealismLora/tree/main
Koss Billingham
2024-10-18 09:12:50 +0000 UTCGuys, where is a full instruction on How to install and use it?
UAknight
2024-10-18 02:57:56 +0000 UTCThis post by Mitsuko E. cleared my problems: "I was able to fix the ControlNet "NoneType" error with these steps: 1. Open ComfyUI Manager menu 2. Select Model Manager 3. Search for "Union" 4. Install "InstantX/Flux.1-dev Controlnet (Union) 5. Refresh or Restart ComfyUI 6. In the Load ControlNet Model node, select "FLUX.1/InstantX-FLUX1-Dev-Union/diffusion_pytorch_model.safetensors" I'm not sure if this is exactly the same controlnet as intended, but it allowed the workflow to generate images and the poses seem to be correct."
Gerard Colin
2024-10-17 16:30:31 +0000 UTC"a character sheet, simpel background, multiple views, from multiple angles, visible face, portrait, Portrait of a 21-year-old scandinavian girl, photography, realistic, instagram" just generated an asian girl. How does this even work?
R0binho0d
2024-10-16 01:03:12 +0000 UTCThe girls generated from this look VERY "robot" like - how do we make a more natural looking girl?
R0binho0d
2024-10-16 00:50:14 +0000 UTCPrompt outputs failed validation: Required input is missing: images SaveImage: - Required input is missing: images VAELoader: - Value not in list: vae_name: 'ae.safetensors' not in ['RealisticVisionV5.1.safetensors', 'taesd', 'taesdxl'] DualCLIPLoader: - Value not in list: clip_name2: 'clip_l.safetensors' not in [] - Value not in list: clip_name1: 't5xxl_fp8_e4m3fn.safetensors' not in [] UNETLoader: - Value not in list: unet_name: 'flux1-dev-fp8.safetensors' not in [] InstantX Flux Union ControlNet Loader: - Value not in list: control_net_name: 'flux\InstantX_flux.safetensors' not in [] how to solve these errors?
Ekka
2024-10-15 22:49:44 +0000 UTCI'm stumped for now... Simply changing the UnionFlux.safetensors to diffusion_Pytorch_model.safetensors does not work. I think it has to do with "Apply Controlnet with VAE" being depreciated. Simply replacing the node with "Apply Controlnet" also fails. I am using the Character Sheet V04 Flux Adv workflow. Thoughts?
Gerard Colin
2024-10-15 21:18:32 +0000 UTCHi everyone! I'm new to all of this, and I'm not entirely sure what ConfyUI is yet, but I'm here because I really need help creating consistent characters. 😅 Congrats on the workflow—it's amazing! I'm trying to get it up and running, but there are so many moving parts that I'm struggling to handle it on my own. When I load the "..V04_FLUX_ADV.json" file, I encounter three errors: ImageBatchMulti, AnyLineArtPreprocessor_aux, and InstantX Flux Union ControlNet Loader. Can anyone point me in the right direction on how to resolve these? Thanks in advance!
Luis Oliveira
2024-10-15 21:09:58 +0000 UTCRight - I've cracked generating enough consistent stuff to train a LoRA. If I'm using FLUXgym, is that only going to work on a FLUX workflow, or am I safe to use the LoRA for SDSX type stuff too? I've skipped FLUX up until now as I couldn't get it to do what I wanted. Edit 1: solved that problem. Trained on SDSX generated images, moved into the Flux workflow. You get much better results if you take the time to tag your training images accurately. If you've got the time/resources, regenerate more of what you want in FLUX (control net works well here) and then create a new data set to train a second LoRA from there. Took me about 5 hours to train each LoRA on 16 epocs with 52 source images (all tagged with paragraphs). Use your desired method of inpainting/img2img/photoshop to touch up the photos before you add them to the data set.
Koss Billingham
2024-10-15 12:20:42 +0000 UTCNot yet, but Mick's working on it. Couple of weeks I reckon.
Baldilocks
2024-10-15 11:04:27 +0000 UTCNot yet, but Mick's working on it. Couple of weeks I reckon.
Baldilocks
2024-10-15 11:04:16 +0000 UTCI had a similar issue. The discord is really helpful as other users can help as well. In this case, open ComfyUI Model Manager and install the "InstantX/FLUX.1-dev Controlnet (Union)" then restart and you should be good to go.
Baldilocks
2024-10-15 11:04:01 +0000 UTCThanks! subbed! you make some great videos. would love to see more flux consistent character workflows. maybe even a LORA guide.
Richard
2024-10-15 10:32:10 +0000 UTCHi there! Just stumbled upon your Youtubechannel yesterday and immediately joined your Patreon! Thank you for all your work! just a question to this workflow...is it possible to connect Loras before the Charaktercreation and if so...where? I am relatively new to ConfyUI. So any help would be great! 🖖 Oh and i am using the FLUX Workflow
Infinity_Reynolds
2024-10-15 09:38:59 +0000 UTCI got error ControlNetApplySD3 'NoneType' object has no attribute 'copy' can you help me how to sorted ?
Tomasz Pasieka
2024-10-14 20:07:17 +0000 UTCThank you immensely for creating this!
Manuel Nixon
2024-10-14 18:52:26 +0000 UTCcan I load an image I have created and if so once I add the node where / how to integrate into the advanced workflow?
Tomasz Pasieka
2024-10-14 17:55:47 +0000 UTCcan I load an image I have created and if so once I add the node where / how to integrate into the advanced workflow?
James McNulty
2024-10-14 14:03:04 +0000 UTCYas!!
Abraham Irawan
2024-10-14 14:02:26 +0000 UTCAfter training Lora, faces gave consistent results, but styles required prompting to get consistent results.
Lee Chars
2024-10-14 00:37:17 +0000 UTCI cannot get FLUX to generate realistic looking people on this, tried the SDSX version and I'm getting nothing but wonky mutants. I've checked the relevant recommended settings on the civitai pages. WildcardTurboXL will generate perfectly good images with similar prompts when not using this workflow - where am I going wrong? Edit - getting somewhere recreating the model step by step (albeit much more rudimentary) - I have managed to generate some decent 3 profile models, however the lines from the control net are showing up as black lines overlayed on the person. Can't seem to prompt them out, any ideas how to sort this out? Edit 2 - for anyone having the same problem, I started a slightly different workflow from scratch, set the image generation to the same resolution as the control net, then set the strength to 0.6. You end up having to do some cherry picking, but it works. Upscaling has mixed results, so you'll need to add a step to fix faces, but using the face detailer module, you can split out a grid of faces using the cropped_refined node and feeding that into individual expression editors. I cut out the face elements of the controlnet and only used the 3 for the body, this saves me having to clip out faces using coordinates. Edit 3 - also, make sure your base image is the same aspect ratio as the control net image, I found I got much better results with the base image generation pixels being exactly double that of the control net.
Koss Billingham
2024-10-13 23:22:28 +0000 UTCYeah me 2! already created a character and want to keep using it.
Bram huisman
2024-10-13 11:50:40 +0000 UTCprobably inside the .zip file
Kelly Christiansen
2024-10-13 04:05:42 +0000 UTCwaiting for it! 🤩
Mert Durmazer
2024-10-12 19:19:39 +0000 UTCWorking on it!
Mick Mahler
2024-10-11 17:54:15 +0000 UTCWhere is the tinaai Lora?
Armando
2024-10-11 02:31:54 +0000 UTChow to join your discord？
noone na
2024-10-10 15:56:22 +0000 UTCwow - amazing work. can you also make a workflow who can create consistent character image to image?
red baron
2024-10-10 15:51:22 +0000 UTC
