README.md

---
library_name: diffusers
pipeline_tag: unconditional-image-generation
tags:
  - diffusers
  - self-flow
  - image-generation
  - class-conditional
  - imagenet
  - flow-matching
license: apache-2.0
inference: true
widget:
  - output:
      url: Self-Flow-XL-2-256/demo.png
language:
  - en
---

# Self-Flow-diffusers

Diffusers-ready checkpoints for **Self-Flow** (Self-Supervised Flow Matching), converted from the [official Self-Flow release](https://github.com/black-forest-labs/Self-Flow) for local/offline use.

This root folder is a model collection that contains:

- `Self-Flow-XL-2-256`

Each subfolder is a self-contained Diffusers model repo with:

- `pipeline.py` (`SelfFlowPipeline`)
- `transformer/transformer_selfflow.py` and weights
- `scheduler/scheduling_flow_match_selfflow.py` (`SelfFlowFlowMatchScheduler`, SDE flow matching)
- `scheduler/scheduler_config.json`
- `vae/` (`stabilityai/sd-vae-ft-ema`)

Each variant embeds English `id2label` in `model_index.json`, so class labels can be passed as ImageNet ids or English synonym strings.

## Demo

![Self-Flow-XL-2-256 demo](Self-Flow-XL-2-256/demo.png)

Class-conditional sample (ImageNet class **207**, golden retriever), `Self-Flow-XL/2` at 256×256, 250 steps, CFG 3.5, seed 42.

## Model Paths

Use paths relative to this root README:

| Model | Resolution | Local path |
| --- | ---: | --- |
| Self-Flow-XL/2 | 256×256 | `./Self-Flow-XL-2-256` |

## Recommended inference

| Setting | Value |
| --- | --- |
| Resolution | 256×256 |
| Sampler | Self-Flow SDE flow matching |
| Steps | 250 |
| CFG scale | 3.5 |
| Guidance interval | `(0.0, 0.7)` when CFG > 1 |
| Dtype | `bfloat16` (recommended on Ampere+) |
| VAE | `stabilityai/sd-vae-ft-ema` |

## Inference Demo (Diffusers)

```python
from pathlib import Path
import torch
from diffusers import DiffusionPipeline

model_dir = Path("./Self-Flow-XL-2-256").resolve()
device = "cuda" if torch.cuda.is_available() else "cpu"

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,
)
pipe.to(device)

generator = torch.Generator(device=device).manual_seed(42)

print(pipe.id2label[207])
print(pipe.get_label_ids("golden retriever"))  # [207]

image = pipe(
    class_labels="golden retriever",
    num_inference_steps=250,
    guidance_scale=3.5,
    generator=generator,
).images[0]
image.save("self_flow_xl_256_demo.png")
```