AI is really only cost-effective for stills and placeholder art. I make a little over $60 per hour in my current position, meanwhile I could go and pay an artist on fiver $10-$20 to animate a still and save myself the trouble. Because remember, my work is worth $60+ an hour, meaning if I hire an artist who would save me 3 or 4 hours worth of work I've effectively saved upwards of $160-220 in time costs.
If you're still invested in learning to do it yourself? Civitai has plenty of workflows and models that when combined can get pretty good results. I think img2vid is what you're actually looking for. Though, you'll most likely need Lora's/Workflow's for each sexual act.
If you're still invested in learning to do it yourself? Civitai has plenty of workflows and models that when combined can get pretty good results. I think img2vid is what you're actually looking for. Though, you'll most likely need Lora's/Workflow's for each sexual act.
You can check out some of ollama's models and see if they have any usefull for vision/art stuff.
ollama is a local AI. like chatgpt but it has a ton of models available.
I am not much into AI art but i asked my ollama about what models are suited for AI art.
Hehe.. dont know if this is any usefull tho
also.
ollama is a local AI. like chatgpt but it has a ton of models available.
I am not much into AI art but i asked my ollama about what models are suited for AI art.
Hehe.. dont know if this is any usefull tho
also.
You must be registered to see the links
You must be registered to see the links
Last edited:
- Jul 4, 2017
- 2,588
- 4,719
Those "ollama" suggestions are all 2 years out of date. Stability.ai's diffusion model release turned the scene on it's head 1.5 years ago.
AmaryPop Check out "lumalabs.ai" for animation - beware tho', it's a service not something you can run locally. Actually, it is my understanding that the memory requirements to run an AI model that is capable of animation are way beyond what is possible in a reasonable home-lab setup. You need like 4x 4090s, or one (or more!) of the datacentre tier cards like A40 or A100 (which cost 1000s of dollars) to run them.
Anya, here's a post with an example I made with lumalabs from a single image and some instructions: https://f95zone.to/threads/the-moor...ish-girl-slow-corruption.205564/post-14111471
AmaryPop Check out "lumalabs.ai" for animation - beware tho', it's a service not something you can run locally. Actually, it is my understanding that the memory requirements to run an AI model that is capable of animation are way beyond what is possible in a reasonable home-lab setup. You need like 4x 4090s, or one (or more!) of the datacentre tier cards like A40 or A100 (which cost 1000s of dollars) to run them.
Anya, here's a post with an example I made with lumalabs from a single image and some instructions: https://f95zone.to/threads/the-moor...ish-girl-slow-corruption.205564/post-14111471