Bernini R 1.3B Int4
Apple MLX port of ByteDance/Bernini-R-1.3B — the 1.3B tier of ByteDance's Bernini Renderer: a Wan2.1-T2V-1.3B-derived video generator/editor with Segment-Aware 3D RoPE for multi-reference / editing tasks. The small...
Source du modèle
- Type
- Text model
- Taille du fichier
- 10,6 GB
- Modèle de base
- ByteDance/Bernini-R-1.3B-Diffusers
- Version
- vt5_encoder
- Mis à jour
- 20 oct. 2026
- Téléchargements
- 77
- Source
- Hugging Face
Description de la source
Bernini-R-1.3B (MLX) — int4
Apple MLX port of ByteDance/Bernini-R-1.3B — the 1.3B tier of ByteDance's Bernini Renderer: a Wan2.1-T2V-1.3B-derived video generator/editor with Segment-Aware 3D RoPE for multi-reference / editing tasks. The small tier "performs close to the 14B variant on simple tasks such as style transfer, subtitle or watermark removal, and local editing."
Runs on Apple Silicon via MLX + the mlx-video Wan backbone.
This is the lowest-cost Bernini tier. For the higher-quality A14B renderer see
mlx-community/Bernini-R-bf16/-int4.
⚠️ Scope: renderer only
Only the Renderer ("-R") is open-sourced upstream. The MLLM semantic planner (the paper's headline "latent semantic planning", a Qwen2.5-VL-7B model) is not released. This port therefore runs with UMT5 text conditioning only — the planner-feature channel is absent (and carries no weights in the released checkpoint).
Architecture
| Backbone | Wan2.1-T2V-1.3B, single expert (30L · dim 1536 · 12H · ffn 8960) |
| Experts | one (skip_transformer_2: true, switch_dit_boundary: 0) |
| VAE | 16-ch AutoencoderKLWan (stock Wan2.1) |
| Text encoder | UMT5-xxl |
| Bernini knobs | shift 3.0, use_src_id_rotary_emb (SA-3D RoPE — no extra parameters) |
Differs from the A14B port only by config: a single 1.3B expert instead of the high/low-noise A14B pair. There is no expert-boundary switch.
Tasks
| Task | Description |
|---|---|
t2v / t2i | text-to-video / image |
r2v | reference-to-video — generate a subject from up to K reference images (chained APG) |
v2v | prompt-based video editing (source video injected as conditioning) |
rv2v | reference + video editing |
Variants
| Repo | Precision | Transformer | + shared |
|---|---|---|---|
...-1.3B-bf16 | bfloat16 | 2.6 GB | VAE 0.5 GB · UMT5 10.6 GB |
...-1.3B-int4 | 4-bit (group 64) | 0.8 GB | VAE 0.5 GB · UMT5 10.6 GB |
Provenance & validation
- Architecture: stock Wan2.1-T2V-1.3B (verified — diffusers
WanTransformer3DModelkeys, no extra tensors; matchesmlx-videowan21_t2v_1_3bexactly: 30L/1536/12H/8960). Bernini knobs (switch_dit_boundary 0,shift 3.0,use_src_id_rotary_emb) live in the wrapper config; SA-3D RoPE adds no parameters. - 4-bit (group 64) quantization of the bf16 conversion of
ByteDance/Bernini-R-1.3B-Diffusers(attention Q/K/V/O + FFN fc1/fc2 only; embeds/norms/head/modulation kept hi-precision). VAE/UMT5 are the shared stock Wan2.1 components, unquantized. - Validated on the CPU stream: key contract bijective (825 file tensors = model params
minus the derived
freqsrope buffer); bf16 forward cosine 0.999983 vs source fp32; int4 per-pass cosine 0.9943 vs bf16 (group 64, ≥0.99 gate).
License & attribution
Apache-2.0. Derived from ByteDance Bernini-R, Wan2.1 (Wan-AI), and mlx-video. See NOTICE.
Sources
1 source
Sources
1 sourceVérifié 20 oct.
Artefacts du modèle
1 artefact
Artefacts du modèle
1 artefactExtraits de sources
3 extraits
Extraits de sources
3 extraits--- license: apache-2.0 library_name: mlx pipeline_tag: text-to-video tags: - mlx - text-to-video - video-editing - video-to-video - reference-to-video - wan2.1 - bernini base_model: ByteDance/Bernini-R-1.3B-Diffusers --- # Bernini-R-1.3B (MLX) — int4 Apple MLX port of **[ByteDance/Bernini-R-1.3B](https://huggingface.co/ByteDance/Bernini-R-1.3B-Diffusers)** — the **1.3B** tier of ByteDance's Bernini *Renderer*: a Wan2.1-T2V-1.3B-derived video generator/editor with **Segment-Aware 3D RoPE** for multi-reference / editing tasks. The small tier "performs close to the 14B variant on simple tasks such as style transfer, subtitle or watermark removal, and local editing." Runs on Apple Silicon via [MLX](https://github.com/ml-explore/mlx) + the [mlx-video](https://github.com/Blaizzy/mlx-video) Wan backbone. > **This is the lowest-cost Bernini tier.** For the higher-quality A14B renderer see > [`mlx-community/Bernini-R-bf16`](https://huggingface.co/mlx-community/Bernini-R-bf16) / > [`-int4`](https://huggingface.co/mlx-community/Bernini-R-int4). ## ⚠️ Scope: renderer only Only the Renderer ("-R") is open-sourced upstream. The MLLM semantic **planner** (the paper's headline "latent semantic planning", a Qwen2.5-VL-7B model) is **not released**. This port therefore runs with **UMT5 text conditioning only** — the planner-feature channel is absent (and carries no weights in the released checkpoint). ## Architecture | | | |---|---| | Backbone | **Wan2.1-T2V-1.3B**, single expert (30L · dim 1536 · 12H · ffn 8960) | | Experts | **one** (`skip_transformer_2: true`, `switch_dit_boundary: 0`) | | VAE | 16-ch `AutoencoderKLWan` (stock Wan2.1) | | Text encoder | UMT5-xxl | | Bernini knobs | `shift 3.0`, `use_src_id_rotary_emb` (SA-3D RoPE — **no extra parameters**) | Differs from the A14B port only by config: a single 1.3B expert instead of the high/low-noise A14B pair. There is no expert-boundary switch. ## Tasks | Task | Description | |---|---| | `t2v` / `t2i` | text-to-video / image | | `r2v` | reference-to-video — generate a subject from up to K reference images (chained APG) | | `v2v` | prompt-based video editing (source video injected as conditioning) | | `rv2v` | reference + video editing | ## Variants | Repo | Precision | Transformer | + shared | |---|---|---|---| | `…-1.3B-bf16` | bfloat16 | 2.6 GB | VAE 0.5 GB · UMT5 10.6 GB | | `…-1.3B-int4` | 4-b...
Source context: 77 downloads · 1 likes · Pipeline text-to-video · Library mlx · Repo mlx-community/Bernini-R-1.3B-int4
Source context: 80 downloads · 1 likes · Pipeline text-to-video · Library mlx · Repo mlx-community/Bernini-R-1.3B-int4
