Views
No views yet
pipeline.py — IMFPipelinescheduler/scheduler_config.json — FlowMatchEulerDiscreteScheduler configtransformer/transformer_imf.py — IMFTransformer2DModelvae/ — bundled stabilityai/sd-vae-ft-mse (AutoencoderKL)
iMF-XL/2 at 256×256, 1 step, CFG 1.8, interval [0.0, 1.0], seed 42.| Checkpoint | Path | Latent size | FID eval CFG (ω) | FID eval interval |
|---|---|---|---|---|
| iMF-B/2 | ./iMF-B-2 | 32×32 | 8.0 | [0.40, 0.65] |
| iMF-L/2 | ./iMF-L-2 | 32×32 | 10.5 | [0.40, 0.60] |
| iMF-XL/2 | ./iMF-XL-2 | 32×32 | 8.0 | [0.42, 0.62] |
1from pathlib import Path
2from diffusers import DiffusionPipeline
3import torch
4
5model_dir = Path("./iMF-XL-2")
6pipe = DiffusionPipeline.from_pretrained(
7 str(model_dir),
8 local_files_only=True,
9 custom_pipeline=str(model_dir / "pipeline.py"),
10 trust_remote_code=True,
11 torch_dtype=torch.bfloat16,
12).to("cuda")
13
14generator = torch.Generator(device="cuda").manual_seed(42)
15image = pipe(
16 class_labels="golden retriever",
17 num_inference_steps=1,
18 guidance_scale=1.8,
19 guidance_interval_start=0.0,
20 guidance_interval_end=1.0,
21 generator=generator,
22).images[0]
23image.save("demo.png")./iMF-XL-2), not the repo root.