Mobius: Redefining State-of-the-Art in Debiased Diffusion Models
Flux lora, trained on the unique style and aesthetic of ghibli retro anime
Flux lora, use "1980s anime screengrab", "VHS quality", or "syntheticanime" to trigger image generation
PrometheusV1 is presumed to be the first full rank finetune of Playground v2.5
ProteusV0.1 uses OpenDalleV1.1 as a base and further refines prompt adherence and stylistic capabilities to a measurable degree
Proteus v0.2 shows subtle yet significant improvements over Version 0.1. It demonstrates enhanced prompt understanding that surpasses MJ6, while also approaching its stylistic capabilities.
ProteusV0.3: The Anime Update
ProteusV0.4: The Style Update
ProteusV0.4: The Style Update - enhances stylistic capabilities, similar to Midjourney's approach, rather than advancing prompt comprehension
ProteusV0.5 is the latest full release built as a sophisticated enhancement over OpenDalleV1.1
This model is cold. You'll get a fast response if the model is warm and already running, and a slower response if the model is cold and starting up.
This model runs on A100 (80GB). View more.
