| --- |
| license: apache-2.0 |
| base_model: black-forest-labs/FLUX.2-klein-base-4B |
| library_name: diffusers |
| pipeline_tag: text-to-image |
| tags: |
| - flux2 |
| - reinforcement-learning |
| --- |
| |
| # Version Base v0.1 Seasonal 39-Family, Step 600 EMA |
|
|
| Complete native BF16 `diffusers.Flux2KleinPipeline`. Trained EMA LoRA weights |
| (rank 32, alpha 64) are merged into the transformer. No FAR or PEFT runtime |
| is needed for inference. |
|
|
| This is the 39-family Version Base v0.1 Seasonal curriculum experiment, not the static |
| AlphaGRPO baseline. Training: 512px, 20 rollout steps, CFG 4, 16 prompts per |
| iteration, group size 14. `100pct` denotes a target, not a verified |
| 100% online-authored fraction. |
|
|
| Source run: `vb-v01-isolated-lifecycle-20260913`. W&B run: `fb24f2db64306fd0bf7dc90c08823fa6`. |
| Exact experiment, source checkpoint hash, source revision, configuration hash |
| and the complete family list are recorded in `provenance.json` and |
| `export_manifest.json`. |
|
|
| `verification.json` records strict offline reloading, nonzero parameter |
| differences from Base before and after serialization, and same-seed |
| 512px/20-step image differences from Base. These checks validate the export; |
| they are not benchmark results or evidence of quality improvement. |
|
|
| ```python |
| import torch |
| from diffusers import Flux2KleinPipeline |
| |
| pipe = Flux2KleinPipeline.from_pretrained( |
| "kimi000/cedar-cloud-83", torch_dtype=torch.bfloat16 |
| ).to("cuda") |
| image = pipe( |
| prompt="A red ceramic teapot beside two blue cups on a wooden table.", |
| height=512, width=512, num_inference_steps=20, guidance_scale=4.0, |
| generator=torch.Generator("cuda").manual_seed(0), |
| ).images[0] |
| ``` |
|
|
