A lora to celebrate the science fiction movies and shows of the 1950s. It's fairly narrowly trained, doing well with space suits, bulky robots and moon-like landscapes.
All images/videos in showcase contain ComfyUI workflows.
Minimax H3:
For all examples I used "50s_scifi" somewhere in the prompt, as well as:
"the image quality is typical 1950s technicolor, with rich, saturated colors."
It hasn't picked up style as well as the concepts from the images, so better prompt it for style.
Possibly loses strength with long generations. All examples are around 3s and use strength 0.7
Krea 2:
Krea 2 can mimick the style fairly well on its own, but a bit of hit and miss, and has the "blandness" several other models have for styles. This lora helps a bit with the style and a few concepts.
Hunyuan 1.5:
First try. All examples done without lightx, 20 steps.
Wan 2.2:
The Low noise lora has absolutely most effect for style. High noise still affects the outcome, but to a much less degree.
For the Wan showcase, I use 25 steps: 15/10. 0.8 strength, and dpm++_sde scheduler in ComfyUI. I haven't had a lot of time for testing, but it might be that it loses strength as you go up in frames.
I use Q4.gguf for High noise, and Q6 for Low noise, for no particular reason. No block swapping.
Wan lora trained with diffusion-pipe.