If you’re one of the many sculptors who sell these things to people like me for a living, should you put all of your 3D renders through Image Generation to produce a painted reference, accepting some slight hallucination for the cheap marketing win?
GENERATIVE AI
-
Chat suggests painting techniques for black dragon miniature
By
–
Asked it what I could do paint wise given intermediate skill level to make it read as a black dragon. I do not know that this is intermediate skill level, Chat, but do sincerely appreciate the painting reference.
-
GPT Engages in Polite Debate Over Dragon Color
By
–
The GPT got into a polite argument with me on whether it was a black or green dragon, resulting in the following delightfully inhuman dialogue.
-
GPT Generates Fantasy Dragon Art from Miniature Description
By
–
It is just ridiculous that this works. (The model is very unfinished, but I thought a visualization might help, and GPT delivered.) Prompt was “Here’s a WIP miniature. Depict this dragon in an appropriate D&D setting, using classic fantasy art style.”
-
Running Large Models on Consumer GPUs: Parallelism and Quantization
By
–
I don't really use GPUs, as most of our work uses TPUs. I was just confused by @jeremyphoward 's statement that it wouldn't run on consumer GPUs, when the normal techniques of model parallelism, quantization, right compression, etc. seem like they should work just fine to run it
-
Model Efficiency on Consumer-Grade GPU Hardware
By
–
Why? It seems as though the model can run on 4 consumer-grade GPUs, no?
-
Running AI Models on Consumer GPUs: Feasibility Analysis
By
–
You can probably run the model on 4 (or maybe 8?) consumer GPUs, no?
-
Transform Content Into Any Material Using ChatGPT
By
–
Turn yourself(ies) into any material using ChatGPT. Super easy, supafast. 3 simple steps:
-
Run Llama 4 Models Easily with vLLM pip Installation
By
–
With vLLM via pip, run any of the models in the Llama 4 family with a simple command.