Tired of boring images and can't be bothered to use controlnet? Use this LoRA and it will add dynamic poses, action camera angles and lots of energy and movement to your images.
Follow me to make sure you see new tools like this, or new styles, poses and Nobodys when I post them. More Clutter series coming too. Things move fast on this site, it's easy to miss.
How to use:
Works at full strength, not overtrained. Use the trigger word zdyna_pose in the positive prompt. Some other useful keywords are posing in zdyna_pose, dutch angle, foreshortening, motion blur, from above, from below, blurred foreground.
Preview Images:
Were generated using ComfyUI and/or InvokeAI. Special thanks to EDG for technical advice in training this concept.
Do you have requests? I've been putting in many more hours lately with this. That's my problem, not yours. But if you'd like to tip me, buy me a beer. Beer encourages me to ignore work and make AI models instead. Tip and make a request. I'll give it a shot if I can. Here at Ko-Fi
Description
FAQ
Comments (15)
Cool concept, I'd love to see it developed even more! Then you could try a different one for dynamic compositions.
loooveeeellllyyy!
I need to take out time and see how to use SDXL
Your A-Zovya RPG model is my favourite, hope to see more from you! Hope to see A-Zovya RPG XL soon ;)
Broken, every time I try to add I get unknown lora type.
what program are you using it in. also did you try re-downloading it
@Zovya Redownloaded it a couple times same result, I'm using Invoke AI
Muy borroso para ser de XL parece Dalee ia
Nice job! do you think is it possible to train a specific pose and making it controllable like Latent Layer Cameras?
Great model, but the characters I generated with it had exactly the same faces. What's the problem?
that's the model's generic face. a model (and the prompts you choose) will make a generic face, LoRAs and other networks can affect that face a little, but not too much. if you don't tell it who to make, it has to come up with something. try "looks like a mix of celebrity1 and celebrity2 together"
You can try an extension like ReActor.
With this A1111/Forge extension you can swap a chosen face or you can made your own custom face if you wish. I've already done about 100 faces.
Although I haven't tried it yet, I understand they have also released a version for ConfyUI.
Probably a dumb question, but can it work on Pony models?. and if not as intended will there be a Pony version of this? :3
Thanks, stuff like this is rare.
It's fascinating that 90% of any given gallery is just random anime porn, lol. I'm positive it's all ESL "tech guys" and "neuro divergents" who can't keep track of themselves for more than 3 fucking seconds
I wonder why there are so many attractive women that have a 3-4 foot dick and just an anus. A lot gays that secretly like woman but just wants a bum hole and a sledge hammer?
It's too bad that all the images in the Gallery are totally static, showing absolutely zero hint of movement. Seems people don't know how to use it and don't bother trying to make it work.
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.