If you can't find the RV Tools use this link https://github.com/whitmell/ComfyUI-RvTools
If you have a bug where the LoRa name appears as [object Object] use this version https://github.com/alcaitiff/ComfyUI-Lora-Auto-Trigger-Words I submitted a merge request from this fork, if the dev read it should be fixed soon.
V2: The workflow has been slightly expanded to include additional features. I have integrated ControlNet's Canny and Depth modules, inpainting capabilities, the Florence prompt generator, and a signature feature at the end. Despite these enhancements, the workflow remains straightforward and user-friendly, with all processes fully automated.
Full flux workflow, with upscaler and saving metadata for civitai. It will clean the lora lines that sometimes happen on Flux, can upscale quit a bit and can do img2img.
This workflow is a merge from my old workflow and this beautiful one https://civarchive.com/models/872281?modelVersionId=981799 made by https://civarchive.com/user/Catz . Please guys donate some buzz to Catz he is a monster.
In the picture I put some numbered marks:
ControlNet - Deph
ControlNet - Canny
Inpainting using Redux
Img2Img area, use if you want or just leave on by pass.
By pass area, you can select what to run on each time. Usually I activate only 1 until I got a good seed and then activate all the others
Your prompt
Save file and metadata for civitai. You can configure what to save. You only need activate one save. Or leave all the yellow boxes active and save at each step
First upscale, this one will increase the details by a good amount. Change the denoise settings as you like, usually is better to leave at 0.52~0.62 but this may change for each style
This step can clean the lora lines if you got no luck on your generation. You may need to change the denoise here too. Usually I leave it on 0.1~0.25.
Extra upscale, sharpness and color adjustments,
Add your signature or watermark on your pictures
Save file and metadata for civitai. You can configure what to save. You only need activate one save. Or leave all the yellow boxes active and save at each step
Load an image and start from 9
Load an image and start from 11
Load an image just to save the civitai info
Florence prompt generator from an image
Your loras, there are 4 but you can increase and just put more groups to the left. Be careful, to many loras may produce some lines on your picture. It happens in flux all the time.
All steps may be by passed and this works super nice.
I added all files on the v1 zip file for convenience, the v2 has only the workflow.
Put the luts inside your ComfyUI/models/luts directory, if you don't have one just create it.
The upscale models go inside your ComfyUI/models/upscale_models
For a grain image you must experiment with some pictures and see what you think is best for you. Some people just don't like it and remove it, some people love it. I think that each style and picture may be a little different in this regard.
Description
The workflow has been slightly expanded to include additional features. I have integrated ControlNet's Canny and Depth modules, inpainting capabilities, the Florence prompt generator, and a signature feature at the end. Despite these enhancements, the workflow remains straightforward and user-friendly, with all processes fully automated.
FAQ
Comments (23)
I get this error when trying to use Depth Anything V2 relative node - -- [Errno 2] No such file or directory: 'D:\\LatestComfyUI\\ComfyUI_windows_portable\\ComfyUI\\custom_nodes\\comfyui_controlnet_aux\\ckpts\\depth-anything\\Depth-Anything-V2-Large\\.cache\\huggingface\\download\\depth_anything_v2_vitl.pth.a7ea19fa0ed99244e67b624c72b8580b7e9553043245905be58796a608eb9345.incomplete'
Looks like your machine is trying to use an incomplete download on this cache directory. Do you have space on this disk? You can download it manually and put on this folder. This is the source https://huggingface.co/depth-anything/Depth-Anything-V2-Large/tree/main
Download the file from here huggingface.co/depth-anything/Depth-Anything-V2-Large/tree/main and put it on this folder -> custom_nodes\\comfyui_controlnet_aux\\ckpts\\depth-anything\\Depth-Anything-V2-Large
@alcaitiff thanks very much, that did fix the problem. Appreciate your help on this
Can you give some instruction on how to use the inpainting sectiion
Sure! Here’s how you can use it in two common scenarios:
Scenario 1: You’ve just started after the basic part but already need to make some changes.
- Enable "6 - Inpaint," "0 - Img2Img," "1 - Basic," and any other nodes you need.
- Place your image in the "Load Image" node under "6 - Inpaint."
- Write a prompt for the new object you want to add (or anything you’d like to replace in the original image).
- Load the "Flux1-fill-dev" model in the "Load Diffusion Model" node.
- Right-click on the loaded image and select "Open in Mask Editor."
- Mask the area you want to change, click "Save," and then run the process.
This will modify the image and pass the updated version through the workflow as if it were created by the basic group.
Scenario 2: You have an almost finished image and want to make a small change.
- Follow the same steps as above, but focus only on the inpainting part until you’re satisfied with the result.
- Once done, right-click on the preview image and save it.
If anything is unclear or you need more details, feel free to ask! I’m happy to help with any specific questions you have.
this uses RVTools but its not available to download on Github any more, PLEASE can you update your workflow or even point us towards a location where we can get RVTools nodes?
Use this one instead https://github.com/whitmell/ComfyUI-RvTools
Got your WF2 and up and running, few questions though: "LoraLoaderStackedAdvanced" Node doesn't show the name of the Lora selected from the drop down list but just [object object] and your image for the workflow shows the showcase image of the lora selected in this node, mine remains empty.
Thanks for this wonderful workflow!!!
I'm glad you liked. For images to show you must download it. Once in a while I boot my old automatic1111 and use the extension civitai helper to download all files. It will show the images on your next comfyui boot. For the object bug, it broke a month ago I think. The developer did not get it right again unfortunately.
One more thing, if ! save images only in basic and on later time I want to selectively make them go through the process of Detailing, upscaling and preprocessing, what would be the steps from the basic stage for this to happen??
@torc007689 if you saved only basic throw it on the img2img area and run again.
@torc007689 I fixed the bug [object Object].
Change your repository on custom notes to https://github.com/alcaitiff/ComfyUI-Lora-Auto-Trigger-Words or just copy my changes on your files. It works now.
I made a pull request to fix the issue on the main server but I don't know if is abandoned.
@alcaitiff I tried replacing the two updated files "utils.py" & "nodes_autotrigger.py" but then I get the missing nodes error for TagSelector and LoraLoaderStackedAdvanced, and if I Uninstall the default custom nodes from the Djikstra and try to install through your git hub link, I get the error from the manager stating "This action is not allowed with this security level configuration."
@alcaitiff I even tried downloading your complete repository as a zip and unzipping and replacing with the original folder in the custom nodes directory but I an still getting [object Object] issue.
@torc007689 after that you must restart comfyui, refresh your page on the browser and re select your loras on the node. I guarantee you that it works.
@alcaitiff Thanks, it works now...actually I didn't selected a new lora from the dropdown list and was in the belief that the pre populated lora in the node should be shown there...any ways I loaded a new lora and it works now...thanks again!!!
@torc007689 I'm glad it worked!
Let's hope the original dev accept the fix and update the official node.
@alcaitiff One more thing, if we load the generated image from the workflow or any of your sample images you have posted here in comfyui, we don't get this exact workflow but more of a stripped down version of it, how can we prevent that?
I can't seem to find out how to add the "RVTools" I checked a comment that said they have the same issues but the links to download don't work anymore. Does that mean i just can't use this workflow?
@alcaitiff when i click on any of the download links, it redirects me to a 404 page
@neekmo3 I think you clicked the broken images, you can ignore those. Either install the nodes via comfy manager (there is an install via url button in there somewhere), or if you want to download and install it manually then on the github page at the top is a green <> Code button at the top, click that and then in that little popup box click download Zip. Worked for me.