v3.1.2 Update:
Added LoRa Stacker
Simplified Loader
More Aspect Ratios and Resolutions
I actually wanted to add the Super Resolution ControlNet, but the integration into ComfyUI isn't working quite right yet. So, this feature will come with the next update.
V3.1 Update:
The V3.1 update now supports the ComfyUI Cascade models.
Additionally, it now has a cascade resolution and aspect ratio node, thus improving the quality of life. Many thanks to "bellamiss" for the node.
The Cascade resolutions custom node is included in the .zip file, just copy the node into the /customnodes folder."
ComfyUi Cascade Checkpoints Link:
V3 Update:
In V2, there was a bug that became apparent when rendering several hundred images, which affected the efficient sampler.
Therefore, I replaced it with the vanilla sampler in V3.
Many thanks for the help with testing to "erosdiffusion" from the L2 Discord.
Furthermore, V3 now has a face detailer that can edit up to 5 different faces.
Optionally, for images with larger faces, the quality of eyes can be improved with the eye detailer.
Eye Yolo Detector Model Link:
More Details LoRa SD 1.5 Link:
Update v3d (Diffusers):
After trying out numerous samplers and configurations, I've decided to go back to using the unofficial DiffusersStableCascade sampler again because it just consistently produces better, more creative images. Feel free to try out the v3 version as well, maybe you'll find a sampler configuration that consistently works well.
Diffusers Stable Cascase ComfyUi Node
It's possible that you encounter errors during installation. Here is a solution approach.
https://github.com/huggingface/diffusers/issues/1619#issuecomment-1345604389
https://huggingface.co/stabilityai/stable-cascade/discussions/17/files
V2 Update:
Comfyui now supports native stable cascade, so the diffusers sampler from v1 is no longer needed. The workflow generates images with sd cascade and improves face details if needed with an sd1.5 model.
The following resolutions work well: 1024x1024 / 1024x1904 / 1024x3808. If you know any other resolutions that work well, please post them here.
I've included a short guide on where to download the models and which folders to copy them into in the red notes of the workflow.
Description
add cascade resolution node
works now with the comfyui cascade models
FAQ
Comments (11)
I'm getting error when load it : When loading the graph, the following node types were not found:
MaskPreview+
ImpactSEGSOrderedFilter
ImpactSimpleDetectorSEGS
Nodes that have failed to load will show as red on the graph.
Install the missing nodes with ComfyUi Manager.
McCascadeRes2 missing and unable to find it
The node is in the zip file. Just copy the folder into your /customnodes folder.
Thank you. Been fairly new i didnt know that but do know. Appreciate your help and great work.
This workflow is excellent. It's obvious that Stable Cascade is capable of really fine details with minimal prompting, and no negative prompt. It seems like the model though has been made to not produce a good result when you try to prompt for anything over PG-13 or 'full body' in it? I wonder if I could throw some SEG nodes in this to refine the bodies of the subjects? Any thoughts on that or what might work as an afterdetailer just for body/clothes? Also, I love the face detailer, and wonder if anyone has tried an inpaint checkpoint for that? I got results where each face was good, but in others, only half of the subjects faces were refined. Epic 1.5 checkpoints are my daily driver so I know those are excellent, and I think its something still with the cascade model censorship, which is weird.
Thanks for making this, it looks awesome. I've managed to install all nodes with no 'red' but get the error 'model.diffusion_model.input_blocks.0.0.weight' while it's processing on the Cascade Stage B node. ComfyUI is updated. any suggestions? can't find any viable solutions in the discussion groups on other sites. I can get cascade working fine on a basic workflow so it's not the cascade b file itself.
Error occurred when executing CheckpointLoaderSimple: 'model.diffusion_model.input_blocks.0.0.weight'
Maby update Comfyui
Wow, really impressive workflow! Wished I understood at least half of the nodes :) Anyway, what impact does the 1.5 model have on the end result, and do you have any suggestion on what model to use? And out of curiosity, why a 1.5 model and not SDXL?
The 1.5 model only improves the face since Cascade still has quite significant issues with smaller faces. In my opinion, the EpicRealism model produces the best, most realistic skin. But you can also use an SDXL model in the face detailer.