Merged with Hyper dev 8 steps lora from Bytedance, Unet only, need clip L, t5xxxl and vae
https://huggingface.co/ByteDance/Hyper-SD/tree/main
Ultimate version
More versatility
Improved artistic side
V4.0
Better realism
Better versatility
Better nudity
Try it with:
Euler/Beta, 10 steps, guidance 3,5 and detail deamon
V3.0
More lora merged for more versatility
Better lighting
Fix vertical trame
V2.7
Merged with my lora: https://civarchive.com/models/866492/moreface-lora
More realism
More versatility
V2.6
More realism, thanks to @bissonfrederic69429 for his wonderful lora SkinDetails
Recommended settings : 10 steps, Guidance 3, Euler/Beta
V2.4
More lora merged
Improve NSFW
More realism
More versatility
Hyper Dev gguf-q4_0 version merged with my lora Real-lora.
Hyper Dev Fp8 Unet version merged with my lora Real-lora.
Hyper Dev bnb nf4 Unet version merged with my lora Real-lora.
https://civarchive.com/models/650205?modelVersionId=727461
More realism for skin, background with less blur.
8 to 20 steps recommended settings : 12 steps, distilled CFG 3, Euler/Beta
Node for comfyui: https://github.com/DenkingOfficial/ComfyUI_UNet_bitsandbytes_NF4
Work with Forge, add vae and clips manualy.
Description
gguf version
FAQ
Comments (8)
I use Forge, if you download the png of the image, you can use the png infos tab of forge to see all of the parameter used.
Feel free to acquire the ComfyUI workflow from the post I just made if you like. Only the last one has been altered (cropped) and won't have that data, the other four will.
hi friend whats the difference between fp8 and gguf?
@dream3 Essentially the file size, gguf can be used on small configurations, with of course a small loss of quality
Does anyone has a comfyUI workflow for this?
The checkpoint seem to be incompatible with many configurations. Always get
TypeError: Flux.forward() missing 1 required positional argument: 'y'
or
'NoneType' object has no attribute 'tokenize'
All WF work for me, just remember for fp8 version, the loader is modele diffusion loader and for the gguf version, the loader is unet loader(gguf)
Depends which one you download, the GGUF version requires a different workflow than regular.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.