Instructions to use PANDATREE/BRIDGE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use PANDATREE/BRIDGE with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("PANDATREE/BRIDGE", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Link released subject-condition data, training guide, and BBox token-control examples
Browse files- flux2-klein-9b/README.md +14 -4
flux2-klein-9b/README.md
CHANGED
|
@@ -61,10 +61,13 @@ background token values into the sub branch; PE routing changes positions.
|
|
| 61 |
|
| 62 |
## Data and examples
|
| 63 |
|
| 64 |
-
The FLUX training
|
| 65 |
-
|
| 66 |
-
|
| 67 |
-
|
|
|
|
|
|
|
|
|
|
| 68 |
|
| 69 |
The accompanying GitHub example is an existing 2026-09-04 Gradio comparison,
|
| 70 |
not a newly generated benchmark. Its metadata identifies these two eval exports
|
|
@@ -73,6 +76,13 @@ is **not** evidence for a token-removal ablation. The source Gradio backend uses
|
|
| 73 |
a CUDA random generator on CUDA; the historical example must not be described
|
| 74 |
as CPU-RNG output. No new image generation was run for this release.
|
| 75 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 76 |
## License
|
| 77 |
|
| 78 |
See [LICENSE.md](LICENSE.md) and [NOTICE.md](NOTICE.md). These weights are FLUX
|
|
|
|
| 61 |
|
| 62 |
## Data and examples
|
| 63 |
|
| 64 |
+
The FLUX training data is now released as the
|
| 65 |
+
[subject-condition extension](https://huggingface.co/datasets/PANDATREE/BRIDGE/tree/main/subject_condition)
|
| 66 |
+
of the existing BRIDGE dataset: 27,834 train / 3,092 test rows and 30,926 selected
|
| 67 |
+
subject references generated with `Qwen/Qwen-Image-Edit-2511`. See the
|
| 68 |
+
[full training guide](https://github.com/XIONGPEILIN/BRIDGE/blob/master/flux2/TRAINING.md).
|
| 69 |
+
BRIDGE uses the same method on both backbones: Qwen uses LoRA plus gates, while
|
| 70 |
+
FLUX uses full-transformer plus gate training.
|
| 71 |
|
| 72 |
The accompanying GitHub example is an existing 2026-09-04 Gradio comparison,
|
| 73 |
not a newly generated benchmark. Its metadata identifies these two eval exports
|
|
|
|
| 76 |
a CUDA random generator on CUDA; the historical example must not be described
|
| 77 |
as CPU-RNG output. No new image generation was run for this release.
|
| 78 |
|
| 79 |
+
Additional [same-BBox-weight cropped-sub comparisons](https://github.com/XIONGPEILIN/BRIDGE/tree/master/flux2/examples/bbox-token-control)
|
| 80 |
+
are now available. Those switch the same BBox checkpoint from dense bbox sub/PE
|
| 81 |
+
support to mask-selected sparse sub/PE support. Six custom-input examples are
|
| 82 |
+
included; internal-dataset examples are excluded. Both token support and PE
|
| 83 |
+
candidate support change. Use the public launcher's `--bbox-protocol-compare`
|
| 84 |
+
option for this mode rather than the default two-trained-checkpoint comparison.
|
| 85 |
+
|
| 86 |
## License
|
| 87 |
|
| 88 |
See [LICENSE.md](LICENSE.md) and [NOTICE.md](NOTICE.md). These weights are FLUX
|