---V7 Notes ---
Prompt adjustments
Improvements to skin textures
More 2.5d/Realism flexibility
Bug fixes and general improvements.
**NOTE - I know that the early access price went up a bit, that's to accommodate for the new system here. I'm still dialing this in and trying very hard to keep this as reasonable as I can. It's a balancing act between this and how much buzz I spend training some things as well as featuring things.
---V6 Notes ---
Better Pony Prompting Adherence
Improved Textures
Fantasy refinements
General Improvements
---V5 Notes ---
Improved Textures
Fantasy Fine Tuning
Better Animals
General Improvements
*Note - This update does not dial back people a ton, so please continue to use specific prompts when you don't want people to appear.
---V4 Notes ---
Anthromorphic Update (variety and quality of people)
Downtuned animal generation
Lighting Improvements
Fantasy Elements Introduced
*Note - This update had a lot of images trained on people. It's going to try to put people in things unless you are very specific in removing them.
---V3 Notes ---
General Improvements
Improved skin textures
Improved animal generation
bug fixes (training to fix bugs) - or however we should say that with models.
--- V2 Notes ---
Improved textures
Improved lighting effects
Better control of light/dark scenes
Better fluid/water rendering
--- V1.021 Notes---
Technically this model is saved as 00Crow-and-Pony (double o) --> reasons...
This is a new Pony model for me, which is trying to leverage what I learned while I've been migrating my Arrogant Bastard model from 1.5 to Pony. This model makes no attempt to bring in any of my 1.5 work, and instead relies on new generations from Arrogant Bastard to build its DataSet. I did create a number of Loras for this, and I strongly consider this version to be a very solid 1.0. I'm pretty happy with it. I'll continue to update my other models as it makes sense, and I am in no way abandoning them. The truth is that this just does different stuff than my other models, even though this is a realistic model also. Please let me know what you think or if you run into any problems. I pay attention and try to incorporate your ideas, and I do go back to fix bugs in future versions.
Description
FAQ
Comments (21)
you can ez-ly set 1000 buzz for early access 4 this great model!
As always, I'm in love with your work
no clothes in my test pictures?!
Love this model. Together with ReActor extension it comes close to Flux (but with better control since it's based on Pony)
What settings have you tried for sampler/scheduler, etc. Testing out now and can't seem to get good results. Not remotely close to example pictures.
@SleezeBagDiffusion Pretty much what was used for most examples. Guidance: 6, Steps: 40, Sampler: DPM++ 2M SDE Heun). Are you using the SDXL vae? I also added the common pony trigger words + some extra trigger words: score_9, score_8_up, score_7_up, BREAK, source_real, raw, photo, amateur (positive) and score_1, score_2, score_3, source_western, source_comic, source_furry, source_anime (negative)
I'll add in here, that Crow & Pony performs fairly well without a VAE set. The PonyStandardVAE_v1 shares a lot of refinements that C&P has built in, so you probably won't notice much of a difference if you use that.
any usage tips? Tried V2 and getting some really awful results. Clip Skip 1 or 2? Specific samplers or schedulers need to be used?
It responds well to fewer negatives. Most of the time I just use a couple score negatives.
I use DPM++ 2m huen and karras a lot.
I tend to use between 30-50 steps. clip skip 1 or 2 should be fine.
I’d recommend grabbing one of my images prompts and settings and tweaking. Double check any up sampler you’re using. I use foolhardy a lot with good results at 1.5 and 30 steps.
i thought we stopped using clip skip after SD1.5 ?
@yofoton174609 pretty much every Pony model requires Clip Skip 2
@soundofmind i tried setting it to -2 and got a nice image with pony. And tried without setting it, and got the same image anyway.
This model does shadows very well. Try adding "in a dimly lit room, soft lighting, hard shadows" to your prompt.
Is it suppose to can't be able to make anthro/furry without using a LoRA?? I've tryed dozens of prompts and failed on all.
It's trained on human imagery, so I expect that a LoRA is going to be your best bet for something specialized.
@QuadPipe Got it. Thank you.
very good
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.