Sponsored by
ThumbnailCreator.com
Minthy / RouWei-0.8-16ch-v0.1alpha
Model's Last Updated: November 04 2025
text-to-image
Introduction of RouWei-0.8-16ch-v0.1alpha
Model Details of RouWei-0.8-16ch-v0.1alpha
Experimental conversion of SDXL architecture to 16 channel latent space
This is an experimental pretrain on top of Rouwei-0.8 that works with 16 channel latent space and uses Flux ae.
Goals:
- Achieve better details while maintaining low compute requirements and all existing knowledge and performance
- Possibility of joint sampling with Flux/Chroma/Lumina and other models with same latent space
Current state:
Early alpha version, it is pretty raw. Images may contain extra noise and have artifacts in small details, level varies from neglectable to significant. Upscale, samplers/schedulers, styles, even prompt affect it.
Use of GAN upscale models in pixels space instead of latent upscale gives much smoother results, bumping base resolution higher helps too.
Epsilon prediction now, can be converted to vpred or anything in future.
Usage:
Comfyui
Workflow example
- Download the checkpoint FP16 ( FP32 weights )
- Download these nodes (or just use "install missing nodes" using Comfy Manager)
-
Use
SDXL 16ch loadernode to load it, then work just like you used to with sdxl
Other UI
Since the main difference is just shapes of tensors, used vae and latents scaling factor - it should be easy to implement support to any other UI.
Lora adapters, controlnet, ip-adapters, other things untested.
Extra examples
(soon)
How it's made
Basically, no changes to default architecture. Just reinitializing if input and output layers to new size, then training with gradual unfreezing of blocks towards the middle.
Default SDXL latent scale factor of
0.13025
doesn't work well here,
0.6
is used for this release.
This is not the most optimal approach. Some changes to the outer layers of the model instead of direct use 'as is' should give improvement in future. If you have any thoughts or ideas about it - please share them.
Training
To train it (in current version) all you need is to change the number of in/out channels in UNET config and set scale factor to 0.6 instead of 0.13025. And probably check vae part to work properly.
(Code examples later)
I'm willing to help/cooperate:
Join Discord server where you can share your thoughts, proposals, requests, etc. Write to me directly here, on civitai or dm in discord.
Thanks:
Part of training was performed using google TPU and sponsored by OpenRoot-Compute
Personal: NeuroSenko
And many thanks to all fellow brothers who supported me before.
Donations:
BTC bc1qwv83ggq8rvv07uk6dv4njs0j3yygj3aax4wg6c
ETH/USDT(e) 0x04C8a749F49aE8a56CB84cF0C99CD9E92eDB17db
XMR 47F7JAyKP8tMBtzwxpoZsUVB8wzg2VrbtDKBice9FAS1FikbHEXXPof4PAb42CQ5ch8p8Hs4RvJuzPHDtaVSdQzD6ZbA5TZ
License:
Same viral as for Illustrious base.
Runs of Minthy RouWei-0.8-16ch-v0.1alpha on huggingface.co
213
Total runs
0
24-hour runs
-7
3-day runs
-43
7-day runs
-52
30-day runs
More Information About RouWei-0.8-16ch-v0.1alpha huggingface.co Model
Url of RouWei-0.8-16ch-v0.1alpha
RouWei-0.8-16ch-v0.1alpha huggingface.co Url
Provider of RouWei-0.8-16ch-v0.1alpha huggingface.co
Other API from Minthy
Total runs:
649
Run Growth:
179
Growth Rate:
27.58%
Total runs:
99
Run Growth:
-19
Growth Rate:
-19.19%
Total runs:
18
Run Growth:
4
Growth Rate:
22.22%
Total runs:
18
Run Growth:
8
Growth Rate:
44.44%
Total runs:
12
Run Growth:
7
Growth Rate:
58.33%
Total runs:
6
Run Growth:
6
Growth Rate:
100.00%
Total runs:
5
Run Growth:
1
Growth Rate:
20.00%
Total runs:
3
Run Growth:
0
Growth Rate:
0.00%
Total runs:
2
Run Growth:
1
Growth Rate:
50.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%