Stable Cascade in ComfyUI with Updated Method and Custom Workflows
ฝัง
- เผยแพร่เมื่อ 8 ก.ค. 2024
- This video provides a guide for running Stable Cascade in ComfyUI with the updated models as well as some custom workflows that address the less desirable aspects of Stable Cascade.
Links
Stable Cascade ComfyUI Examples: comfyanonymous.github.io/Comf...
Stable Cascade ComfyUI Checkpoints: huggingface.co/stabilityai/st...
Stable Cascade 2-Pass HiRes Fix: comfyworkflows.com/workflows/...
Stable Cascade 3-Pass HiRes Fix: comfyworkflows.com/workflows/...
Stable Cascade 2 SDXL: comfyworkflows.com/workflows/...
ControlNet Aux Preprocessors: github.com/Fannovel16/comfyui...
ControlNet Loras for SDXL: huggingface.co/stabilityai/co...
JuggernautXL V9 SDXL Checkpoint: civitai.com/models/133005?mod...
Chapters
0:00 Overview
0:21 Downloads and Set Up for Stable Cascade
2:03 Explore and Explain the Examples
7:30 Custom Workflows, Why?
8:37 Stable Cascade "HiRes Fix" (2 Pass)
12:47 Stable Cascade 2 SDXL
17:39 Stable Cascade "HiRes Fix" (3 Pass)
*Narration created using Elevenlabs' SpeechToSpeech Synthesis - แนวปฏิบัติและการใช้ชีวิต
finally, some guide that i can comprehend and follow, and then even play around with it. You are so kind to even list all the resources in the description in an well-organized manner.
instant sub from me.
Fantastic, I appreciate the time taken to detail explain some concepts and the general easy , unhurried tone
Excellent! Great explanation.
I really have not figured out the applicablility of cascade yet, thanks for sharing this all the same
I’ve noticed its biggest strengths are composition and text while still allowing variety in output. There are some great fine tunes for SDXL out there that offer better composition for certain styles, but can be more limited in their breadth. Honestly though, I think the main upside of Stable Cascade is not the current checkpoint, but the method and how it allows for creating fine tunes at a reduced cost.
Much Better explanation of Cascade in Comfiui. Thank you. Will try this today. The b to c and then a is a bit confusing and works sometimes. This is much simpler and requires less files.
im amazed that no one has ever thought of Combining Stable Forge with Both Krita and Cascade it would actually solve a lot of problems
I do agree with the overbaked look.
Thanks!
Thank you for sharing! Subscribed:)
I have a question about AIO Aux Preprocessor in 2 SDXL workflow. I don't see LineartStandardPreprocessor option, closet one is LineartPreprocessor, but it throws error
"Error occurred when executing AIO_Preprocessor:
LineartDetector.from_pretrained() got an unexpected keyword argument 'cache_dir'"
Never mind, I have it resolved. I replaced both with "[Inference.Core] AIO Aux Preprocessor" which has the option. Hope this could help others
thanks... is there a workflow to fix faces and hands with cascade?🤗
I've been working on one for faces that I'll be sharing in an upcoming video. In the meantime, explore this node (github.com/mav-rik/facerestore_cf) in combination with HiRes fix. For hands, you might try HandRefinder (github.com/wenquanlu/HandRefiner) which is included with the controlnex_aut preprocessors for ComfyUI (github.com/Fannovel16/comfyui_controlnet_aux).
hi can you help me to solve this error "module diffuser has no attribute StableCascadeUnet. i installed cascade install in stable diffusion but i got this error after installing of all model on window 11
It sounds like your diffusers package may be out of date. If you haven’t already, try updating ComfyUI. If you have the Windows portable install you can go into ComfyUI_windows_portable/update folder and run `update_comfyui_and_python_dependencies.bat`.
question, what happened to stable cascade stage a (VAE)? I don't see it
edit: ok got the answer, another person already asked it before
Anyway, subscribed. cause not many ppl experimenting with stable cascade and sharing their findings like you
Where is vae "stage_a"? or is this not necessary?
Not necessary as a separate model for this method. It’s been baked in as the VAE of the stage b checkpoint for the ComfyUI-specific models.
I do wish you can make the noodles less noticable ha
Usually I'll adjust it for myself to make things look cleaner, but it makes it harder to see what the connections are so I switch it to ultimate noodle mode for videos. You can change it by clicking the gear in the menu to the right and switching the Link Render mode.
Are you on discord?
Not currently, but it's probably about time for me to make an account and get on there. 😅
Stable Cascade takes too long only to create images that are not truly better
I agree for the most part. There are a few things it can do better than other models without special nodes, such as text and higher resolutions, but in general I think its strengths won’t really show until some fine tunes come out. That said, given its current licensing and the upcoming SD3 release, that may not matter much either.