Wan
Collection
2 items • Updated
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Rin247/Wan2.2-TI2V-5B-Diffusers", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Wan2.2-TI2V-5B-Diffusers
Quantised media packages of Wan-AI/Wan2.2-TI2V-5B.
MECHA Forge
MECHA — Model Engineering & Contextual Hearth Assembly
These media packages have been forged and optimized in the MECHA Forge. Each one holds the Denoiser, Text Encoder, and VAE components packaged together for easier deployment.
Description
Wan 2.2 TI2V 5B: text/image-to-video at 720P 24fps. 40 steps, CFG 5.0.
Available quantizations
| Quant | Denoiser | Text encoder | VAE |
|---|---|---|---|
| FP4 | FP4 | FP4 | FP8 |
| FP8 | FP8 | FP8 | FP8 |
| INT4 | INT4 | INT4 | INT8 |
| INT8 | INT8 | INT8 | INT8 |
The VAE is shared between formats: FP4 reuses the FP8 file, INT4 reuses the INT8 file.
Recommended settings
From the source model card (adjust to taste):
| Parameter | Value |
|---|---|
| Steps | 40 (default) |
| CFG / Guidance scale | 5.0 |
| Resolution | 1280x704 (720P) |
| Notes | TI2V: text/image-to-video, 24fps |
Example prompts
Caught in the moment (candid, slice of life):
masterpiece, best quality, highres, absurdres, very aesthetic, safe, 1woman,
solo, candid moment, natural lighting. A beach boardwalk at sunset, golden sky,
waves in the background, warm breeze. A 30-year-old woman with high cheekbones
and green eyes. She has an athletic build and a relaxed expression. She wears a
sundress and sandals, holding a camera, mid-smile, candid and relaxed.
Fashion photography (magazine cover style):
Fashion video still: a 30-year-old woman with high cheekbones, green eyes, and
full lips; wearing a flowing red gown, gold jewelry; wind, dramatic lighting,
cinematic, 24fps, 8K.
Scenery:
Scenery: a sweeping aerial of a tropical island, turquoise water, white sand,
palm trees, golden hour, boats, 8K.
- Downloads last month
- 112
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support