Note: I spend a lot of time on these to make sure they are top notch. If you have ANY issues, I'm very responsive. hit me up and I'll resolve them for you.
This is a V1 version. I do not know this model or how it gets used. Please let me know what you woudl liek to see or need, or better yet, what settings youa re used to using as I am clueless on this one
Instagram: https://www.instagram.com/synth.studio.models/
Buy me a☕ https://ko-fi.com/lonecatone
This represents many of hours of work. If you enjoy it, please 👍like, 💬 comment , and feel free to ⚡tip 😉
也有中文说明
This is an all in one workflow:
I2I with prompt generation
i2I manipulation
Style manipulation
Can use the Full, Fast, or GGUF models without having to rewire or change anything
Sage Attention: Speeds up production
Advanced Clowshark KSampler
Ultimate upscaler: For prescale and hi-res fix
Detailers: Face, eyes, hand, expression
Seed VR2 Upscaler: Get up to 4k pics, even on low VRAM
Post production suite: My pride and joy. Does everything.
Does NSFW
Uses standard nodes so you don't have to download one that someone stole from Sam Shark (Res4lyf) and renamed.
Description
FAQ
Comments (2)
Thanks for sharing this workflow — I can see a lot of effort went into organizing all the modules and options. It’s very useful as a reference for older HiDream setups.
I noticed the workflow still seems to follow the earlier HiDream I1/E1 structure with separate text encoders, VAE loaders, and GGUF-based components. From what I understand, the newer O1/checkpoint-style releases are becoming more self-contained, so it might be cleaner and easier for users if future versions move toward direct checkpoint loading instead of relying on multiple external encoder/vae nodes.
That could probably reduce dependency issues and make the workflow much easier to maintain across newer ComfyUI versions as well.
Just a suggestion — and thanks again for making the workflow public and sharing your work with the community.
I appreciate the feedback. I'm not sure how I feeel about this model. I tried messing with the O1 style. I can easily slap a checkpoint module in there as well.
I want to see what the feedback is on this workflow. It takes a lot to maintain all of the ones I have.