Ver2ish:
Attempted to improve prompt following and get rid of some of the ocasional multi-limbed eldritch horrors. Sample images generated using ComfyUI single pass without high-res fix (mostly using either ChatGPT or a local LLM to improve the prompts)
It's capable of some NSFW, but has the usual issues with ... lets call it intimate anatomy.
Suggested Generation Parameters:
Sampler: Euler_a
Scheduler: normal
Steps: 8
CFG: 1.2
________
Lightning8 Beta1 - 23 Feb 2024:
A merge of FastPass core and Lightning8 step.
Suggested Generation Parameters:
Sampler: Euler_a
Scheduler: normal
Steps: 8
CFG: 1.2
____
This merge combines a handful of my favorite realistic models and Lora, along with both LCM and SDXL Turbo Lora extractions. It's fast. Blazingly fast. It's also sometimes a little fickle, and ... set in its ways.
Performs best at very high native resolutions - 1024x1360 using Kohya's Deep Shrink Hi-res fix and very simple negative prompts.
Best Settings:
Steps: 4-8
CFG: 1.3-1.6
Resolution: 1024x1360 or derivatives
Generation time 2-5 seconds on a 12GB RTX 3060
I haven't tried many Loras with it, so YMMV.
Description
First release version. Includes LCM and Turbo extracts. Use 4 -8 steps, LCM scheduler, and Kohya Hi-res. Best at 1024x1360 or equivalent pixels.
FAQ
Comments (9)
Where i get LCM sampler from?
Install AnimateDiff ...
Or ... it's built into ComfyUI's samplers.
@zackstone Thx!
I made some grids of all currently uploaded turbo models. all but the base model and jib's need atleast 3 steps for a decent image, and anything over config 2 tends to be either very cartoony or blurry/other artifacts. also almost no difference between 1 step and 2 steps.
(step check 1-4, cfg1)https://civitai.com/posts/929205
(cfg check, 4steps)https://civitai.com/posts/929178
(same model order as pervious grids, cfg 1 steps 3) https://civitai.com/posts/929237
This is the best (by far) photorealistic turbo model currently available on CivitAI. Needs more fine tuning for more natural poses and expressions, as sdxl turbo really sucks in that respect. Keep up the good work.
Amazing model thanks Upsidedownsquirrel for sharing, please share how you merge a "standard" model with a LCM or turbo, please? Did you use the LCM LORA and merge it with a standard model? and then with the SD turbo? Thanks again and have a great day!
I should have responded to this a while ago ... sorry.
I'm using ComfyUI to build the merges, it allows you to add the loras/weights into the model before saving. Effectively, I merge several modes, then merge in the loras, then save the model.
Any chance of a pruned FP16 model?
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.