Fibo 2.0 for WanGP

Prepared BF16 and INT8 ConvRot checkpoints for WanGP. Credit to Bria AI, creators of Fibo 2.0 Dev and Fibo 2.0 Edit Turbo.

Model Workflows Starting settings
Dev Text-to-image, reference editing and masked editing 50 steps, guidance 5
Edit Turbo Reference and masked editing; source image required 4 steps, guidance 1

Both accept up to four ordered references and optional structured captions. In WanGP, Main Image Ref derives the output dimensions from the first reference; the alternate reference mode keeps the selected dimensions. Masked editing uses one image and mask. Outside-mask pixels and exact requested object counts are not guaranteed.

Transformer checkpoints are at the repository root. The shared Qwen3-VL-4B-Instruct conditioning encoder and tokenizer are in Qwen3-VL-4B-Instruct/; the FP16 Flux2 VAE and optional text-rendering fonts are in fibo2/. These are WanGP checkpoints, not a complete Diffusers pipeline directory. Place files in the same relative hierarchy under WanGP's checkpoint directory, or let WanGP download the selected format.

BF16 transformers retain the original tensor values. INT8 uses ConvRot with BF16 unquantized parameters and FP32 quantization scales. The VAE has FP16 parameters and preserves its FP32 normalization statistics. Both formats were validated with real generation/editing through WanGP and MMGP; enhancement remains opt-in.

Sources and licensing

These are repackaged/quantized derivatives, not new base models. Upstream revisions:

  • Dev: 530604492bf2bd1364ae43ca6b2bf2285ef0f2ba
  • Edit Turbo: 63316ff6d5c4c4ba37729a8a6510bced7e8f585b

Bria's model license and restrictions continue to apply. The upstream model cards link to CC BY-NC 4.0 and state that commercial use requires a separate agreement with Bria; see Bria licensing. Original model cards are retained under upstream/ for attribution and terms. Qwen conditioning and the Flux2 autoencoder retain their respective upstream terms: Qwen3-VL and FLUX.2. Aileron and DejaVu retain the license files shipped beside the fonts.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for DeepBeepMeep/Fibo2

Finetuned
(5)
this model