import torch
from diffusers import DiffusionPipeline
from diffusers.utils import export_to_video
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Wan-AI/Wan2.1-T2V-1.3B", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("AlekseyCalvin/HSToricColorT2VWan1.3B_v2_rank128LoRA_bySilverAgePoets")
prompt = "HST style analog autochrome film clip, close up"
output = pipe(prompt=prompt).frames[0]
export_to_video(output, "output.mp4")HSToric Color Film Version 2: Rank 128
Text to Video Low Rank Adapter (LoRA)
For the Wan2.1 1.3B T2V Base Model
|||||| By SilverAgePoets.com ||||||
This is the second Text to Video addition to our HSToric Color text-2-image model adapter series.
Like some of the other HST color models, this variant was trained on HD scans of early color photos (circa 1900s-1910s ) by Sergey Prokudin-Gorsky, who traveled and photographed widely in those years whilst perfecting implementations of a pioneering 3-color-composite photography technique.
This model is aimed at being useful for:
- Improving the realism and detailing of Wan1.3B, and creating clips exhibiting more consistent similarities to real analog color film.
- Producing clips with a vaguely "historical" or "lived-in" aesthetic character, striking chromaticity and luminosity dynamics, as well as textural/anatomical/skin details more reliably lifelike than through the use of other suchlike-use-case-catered adapters.
For the best among our several T2I Flux variants of this LoRA, see Historic Color Dedistilled, fine-tuned over the Colossus 2.1 Dedistilled Model, a modified Flux-family model by Afroman4peace.
Trigger words
You should use HST style analog autochrome film clip, close up to open a vivid window into a chromatically bewitching ever-futurous past.
- Downloads last month
- 11
Model tree for AlekseyCalvin/HSToricColorT2VWan1.3B_v2_rank128LoRA_bySilverAgePoets
Base model
Wan-AI/Wan2.1-T2V-1.3B