0
stars
15
commits
1
linked in READMEs
May 30, 2026
updated
class-conditional
diffusers
image-generation
imagenet
pmf
safetensors
text-to-image
README
pMF-diffusers
Native diffusers implementation of Pixel Mean Flows (pMF). Each variant folder is self-contained:
pipeline.py—PMFPipelinescheduler/scheduler_config.json—FlowMatchEulerDiscreteSchedulerconfigtransformer/transformer_pmf.py—PMFTransformer2DModeltransformer/— converted weights and config
Available checkpoints
| Checkpoint | Path | Resolution | Recommended CFG (ω) | CFG interval | Noise scale |
|---|---|---|---|---|---|
| pMF-B/16 | ./pMF-B-16 | 256×256 | 7.5 | [0.1, 0.8] | 1.0 |
| pMF-B/32 | ./pMF-B-32 | 512×512 | 6.5 | [0.1, 0.7] | 2.0 |
| pMF-L/16 | ./pMF-L-16 | 256×256 | 7.0 | [0.2, 0.7] | 1.0 |
| pMF-L/32 | ./pMF-L-32 | 512×512 | 7.5 | [0.2, 0.6] | 4.0 |
| pMF-H/16 | ./pMF-H-16 | 256×256 | 7.0 | [0.2, 0.6] | 2.0 |
| pMF-H/32 | ./pMF-H-32 | 512×512 | 5.5 | [0.1, 0.6] | 4.0 |
Inference
from pathlib import Path
from diffusers import DiffusionPipeline
import torch
model_dir = Path("./pMF-L-16")
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.float32,
).to("cuda")
generator = torch.Generator(device="cuda").manual_seed(42)
image = pipe(
class_labels="golden retriever",
num_inference_steps=1,
guidance_scale=7.0,
guidance_interval_min=0.2,
guidance_interval_max=0.7,
noise_scale=1.0,
generator=generator,
).images[0]
image.save("demo.png")
Load a variant subfolder (e.g. ./pMF-L-16), not the repo root.
Contributors
BiliSakura
15 commits
Similar repos
0
stars
15
commits
1
linked in READMEs
May 30, 2026
updated
class-conditional
diffusers
image-generation
imagenet
pmf
safetensors
text-to-image
README
pMF-diffusers
Native diffusers implementation of Pixel Mean Flows (pMF). Each variant folder is self-contained:
pipeline.py—PMFPipelinescheduler/scheduler_config.json—FlowMatchEulerDiscreteSchedulerconfigtransformer/transformer_pmf.py—PMFTransformer2DModeltransformer/— converted weights and config
Available checkpoints
| Checkpoint | Path | Resolution | Recommended CFG (ω) | CFG interval | Noise scale |
|---|---|---|---|---|---|
| pMF-B/16 | ./pMF-B-16 | 256×256 | 7.5 | [0.1, 0.8] | 1.0 |
| pMF-B/32 | ./pMF-B-32 | 512×512 | 6.5 | [0.1, 0.7] | 2.0 |
| pMF-L/16 | ./pMF-L-16 | 256×256 | 7.0 | [0.2, 0.7] | 1.0 |
| pMF-L/32 | ./pMF-L-32 | 512×512 | 7.5 | [0.2, 0.6] | 4.0 |
| pMF-H/16 | ./pMF-H-16 | 256×256 | 7.0 | [0.2, 0.6] | 2.0 |
| pMF-H/32 | ./pMF-H-32 | 512×512 | 5.5 | [0.1, 0.6] | 4.0 |
Inference
from pathlib import Path
from diffusers import DiffusionPipeline
import torch
model_dir = Path("./pMF-L-16")
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.float32,
).to("cuda")
generator = torch.Generator(device="cuda").manual_seed(42)
image = pipe(
class_labels="golden retriever",
num_inference_steps=1,
guidance_scale=7.0,
guidance_interval_min=0.2,
guidance_interval_max=0.7,
noise_scale=1.0,
generator=generator,
).images[0]
image.save("demo.png")
Load a variant subfolder (e.g. ./pMF-L-16), not the repo root.
Similar repos
Contributors
BiliSakura
15 commits