Text-to-Image
Diffusers
Safetensors
English
FluxPipeline
flux
fluxpipeline
schnell
photography
analog
vintage
photorealism
fine-tune
checkpoint
DiffusersPipeline
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("AlekseyCalvin/mytHSTic-merge_Soonr-Flux_Diffusers_fp8", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]mytHSTic color SOON®: a Fast (3-8 steps) Flux Model by A.C.T. SOON®
A further development of the historic/vintage/analog photo concept also found in my Historic Color Flux LoRAs and Models. This checkpoint merges in, over Pixelwave Schnell V.1, three different Historic Color LoRAS, trained with distinct datasets over different targeted model Layers. Additionally, it lightly merges in a LoRA distillation of STOIQO New Reality by ALIENHAZE and the anti-blur LoRA.
- Downloads last month
- 5
Model tree for AlekseyCalvin/mytHSTic-merge_Soonr-Flux_Diffusers_fp8
Base model
black-forest-labs/FLUX.1-schnell