BiliSakura/iMF-diffusers

Model

0

stars

8

commits

2

linked in READMEs

May 30, 2026

updated

class-conditional
diffusers
image-generation
imagenet
imf
safetensors
text-to-image
Browse cluster: Diffusion Models & Image Generation

README

iMF-diffusers

Native diffusers implementation of Improved Mean Flows (iMF). Each variant folder is self-contained:

  • pipeline.pyIMFPipeline
  • scheduler/scheduler_config.jsonFlowMatchEulerDiscreteScheduler config
  • transformer/transformer_imf.pyIMFTransformer2DModel
  • vae/ — bundled stabilityai/sd-vae-ft-mse (AutoencoderKL)

Demo

iMF-XL-2 demo

Class-conditional sample (ImageNet class 207, golden retriever), iMF-XL/2 at 256×256, 1 step, CFG 1.8, interval [0.0, 1.0], seed 42.

Available checkpoints

CheckpointPathLatent sizeFID eval CFG (ω)FID eval interval
iMF-B/2./iMF-B-232×328.0[0.40, 0.65]
iMF-L/2./iMF-L-232×3210.5[0.40, 0.60]
iMF-XL/2./iMF-XL-232×328.0[0.42, 0.62]

FID eval settings follow upstream imeanflow eval config.

Inference

from pathlib import Path
from diffusers import DiffusionPipeline
import torch

model_dir = Path("./iMF-XL-2")
pipe = DiffusionPipeline.from_pretrained(
    str(model_dir),
    local_files_only=True,
    custom_pipeline=str(model_dir / "pipeline.py"),
    trust_remote_code=True,
    torch_dtype=torch.bfloat16,
).to("cuda")

generator = torch.Generator(device="cuda").manual_seed(42)
image = pipe(
    class_labels="golden retriever",
    num_inference_steps=1,
    guidance_scale=1.8,
    guidance_interval_start=0.0,
    guidance_interval_end=1.0,
    generator=generator,
).images[0]
image.save("demo.png")

Load a variant subfolder (e.g. ./iMF-XL-2), not the repo root.

Contributors

BiliSakura

8 commits

BiliSakura/iMF-diffusers

Model

0

stars

8

commits

2

linked in READMEs

May 30, 2026

updated

class-conditional
diffusers
image-generation
imagenet
imf
safetensors
text-to-image
Browse cluster: Diffusion Models & Image Generation

README

iMF-diffusers

Native diffusers implementation of Improved Mean Flows (iMF). Each variant folder is self-contained:

  • pipeline.pyIMFPipeline
  • scheduler/scheduler_config.jsonFlowMatchEulerDiscreteScheduler config
  • transformer/transformer_imf.pyIMFTransformer2DModel
  • vae/ — bundled stabilityai/sd-vae-ft-mse (AutoencoderKL)

Demo

iMF-XL-2 demo

Class-conditional sample (ImageNet class 207, golden retriever), iMF-XL/2 at 256×256, 1 step, CFG 1.8, interval [0.0, 1.0], seed 42.

Available checkpoints

CheckpointPathLatent sizeFID eval CFG (ω)FID eval interval
iMF-B/2./iMF-B-232×328.0[0.40, 0.65]
iMF-L/2./iMF-L-232×3210.5[0.40, 0.60]
iMF-XL/2./iMF-XL-232×328.0[0.42, 0.62]

FID eval settings follow upstream imeanflow eval config.

Inference

from pathlib import Path
from diffusers import DiffusionPipeline
import torch

model_dir = Path("./iMF-XL-2")
pipe = DiffusionPipeline.from_pretrained(
    str(model_dir),
    local_files_only=True,
    custom_pipeline=str(model_dir / "pipeline.py"),
    trust_remote_code=True,
    torch_dtype=torch.bfloat16,
).to("cuda")

generator = torch.Generator(device="cuda").manual_seed(42)
image = pipe(
    class_labels="golden retriever",
    num_inference_steps=1,
    guidance_scale=1.8,
    guidance_interval_start=0.0,
    guidance_interval_end=1.0,
    generator=generator,
).images[0]
image.save("demo.png")

Load a variant subfolder (e.g. ./iMF-XL-2), not the repo root.

Contributors

BiliSakura

8 commits