Note: If you have ANY issues with nodes not downloading, read the notes or reach out. There's nothing that special about any of them that aren't core modules.
⛔⚠️🛑✋ Read the notes completly before using. Most common install and node problems are listed in the directions
也有中文说明
A complete user and troubleshooting guide inclusing a list of common error messages can be found here https://civarchive.com/articles/24678/how-to-use-my-workflows-a-comprehensive-breakdown
Instagram: https://www.instagram.com/synth.studio.models/
Buy me a☕ https://ko-fi.com/lonecatone
This represents hundreds of hours of work that I give away for free. If you enjoy it, Please make sure to 👍like and post to my workflows. That is how you support me. Also, feel free to ⚡tip 😉
What's Included
Checkpoint/ GGUF/ and basic model loader
works on Turbo as well as base.
Prompt generation
Lora Loader
Draft mode for making corrections without having to rerun the workflow.
Ultimate Upscaler for prescaling and hi res fix
Simple Detailing Suite for face & eyes
Seed VR2 Upscaler to get 4k on low VRAM
Essential Post Production Suite
Smart Noise scrubber
Full tutorial available.
也有中文说明
Optical realism (BETA): Give me feedback on this please. It works well, but not so sure it helps everything.
Adds depth to images
Depth enhanced film grain
Wraps the background over the egdes of the image to eliminate the cardboard cutout look
Look, it's just badass. Mess with it, see if you like it and let me know.
Check out my other models:
My NSFW version with Anantomy Correctors:https://civarchive.com/models/2270894/zit-nsfw-anatomy-corrector
For ultimate Anime detail and control: https://civarchive.com/models/2220766/zimage-ultra-anime-detail-workflow-get-the-most-out-of-your-generations
For Realism and variety over the base model: https://civarchive.com/models/2231181/z-image-ultra-real-workflow
Description
FAQ
Comments (8)
Nice work. Changing 'CLIP Set Last Layer' to -1 helps some quality.
Man, You ahve no idea how many hours wasted on this. I'm not a fan of Base. I'll put that in the notes.
Thanks
Well, I appreciate you sharing the fruits of your labor. I am optimistic base will end up being good. Just needs training by those with more skill than myself, still learning. But I find tweaking the weight_dtype in the diffusion loader and bumping the clip to grab the additional layer makes a difference.
hi..
I get this error right off the bat:
[GetNode] ✗ Variable 'Upscale Image' not found! Available: Height, Width, Upscale factor Tip: Make sure SetNode runs BEFORE GetNode in the graph.
I didn't touch anything but the model, clip & vae
look and see if teh anything everywhere node is connected. are you on Desktop?
Oh yah. I've seen that before. You need to update KJ nodes. Open your manager and hit "Update all"
thanks. I actually ended up having to revery back to the old manager and get everything updated through that. Dunno why. But no more errors. :-)
@Symbiot78 Are you on desktop? You can thank ComfyUI for pushing a version that doesn't align with the new Torch 5.0 and Cuda


