Bernini-v2 int4 MLX variant (experts 4-bit gs64; planner/T5/VAE bf16)

README.md

@@ -0,0 +1,28 @@
+---
+license: apache-2.0
+base_model: ByteDance/Bernini-Diffusers-v2
+tags:
+- mlx
+- video
+- text-to-video
+- image-to-video
+- video-editing
+- wan
+- bernini
+library_name: mlx
+---
+
+# Bernini-v2 (int4, MLX)
+
+4-bit variant of [`mlx-community/Bernini-v2-bf16`](https://huggingface.co/mlx-community/Bernini-v2-bf16)
+— Apple-MLX conversion of [ByteDance/Bernini-Diffusers-v2](https://huggingface.co/ByteDance/Bernini-Diffusers-v2)
+(revision `399cf6a`, Apache-2.0).
+
+**Quantization scope:** the two Wan2.2-A14B transformer experts only (attention + FFN Linears,
+4-bit, group size 64; embeddings/norms/head/modulation stay bf16). The planner plane
+(`mllm/`, `vit_decoder`, `planner_glue`), umT5 encoder, and VAE pass through at bf16 —
+weight-only int4 on diffusion transformers costs measurable quality (bf16 is the recommended
+default; this variant is the memory-constrained opt-in).
+
+See the bf16 repo's card for the full component table, conversion notes, retrained-experts
+warning (not interchangeable with `Bernini-R-*`), usage pointers, and provenance.

bernini_v2_config.json

@@ -0,0 +1,50 @@
+{
+  "model_type": "bernini",
+  "architectures": ["BerniniModel"],
+  "mllm_attn_implementation": "sdpa",
+  "partial_pretrain_model": "",
+  "base_dir": "ByteDance/Bernini-Diffusers",
+  "vae_subfolder": "vae",
+  "cotrain": true,
+  "boundary_ratio": 0.417,
+  "switch_dit_boundary": 0.875,
+  "shift": 3.0,
+  "logit_mean": 0.5,
+  "logit_std": 1,
+  "mode_scale": 1.29,
+  "scratch": true,
+  "transformers_version": "4.57.3",
+  "mllm_subfolder": "mllm",
+  "processor_subfolder": "mllm",
+  "bernini_ckpt_subfolder": "bernini",
+  "scratch_mllm": true,
+  "use_src_id_rotary_emb": true,
+  "feature_type_from_stage_one": "masked_tgt_embed_with_qwen_txt_vit_tokens",
+  "num_mask_token": 4096,
+  "max_sequence_length": 512,
+  "clip_diff_cfg": {
+    "model_type": "flow_match",
+    "z_channels": 3584,
+    "target_channels": 3584,
+    "width": 4096,
+    "diffusion_batch_mul": 16,
+    "shift": 2.0
+  },
+  "connector_cfg": {
+    "model_type": "MLPConnector",
+    "out_dim_for_gen": 4096,
+    "enable_gen_branch": true,
+    "out_dim_for_vit": 3584,
+    "enable_vit_branch": true,
+    "gen_head_type": "zerolinear",
+    "zero_init_proj_gen_last": true
+  },
+  "mask_ratio_infer_cfg": {
+    "generator_type": "default"
+  },
+  "t5_max_sequence_length": 512,
+  "t5_text_encoder_subfolder": "t5_text_encoder",
+  "t5_tokenizer_subfolder": "t5_tokenizer",
+  "t5_combine_type": "concat_with_zero_init",
+  "target_fps": 16
+}

config.json

@@ -0,0 +1,55 @@
+{
+  "model_type": "t2v",
+  "model_version": "2.2",
+  "patch_size": [
+    1,
+    2,
+    2
+  ],
+  "text_len": 512,
+  "in_dim": 16,
+  "dim": 5120,
+  "ffn_dim": 13824,
+  "freq_dim": 256,
+  "text_dim": 4096,
+  "out_dim": 16,
+  "num_heads": 40,
+  "num_layers": 40,
+  "window_size": [
+    -1,
+    -1
+  ],
+  "qk_norm": true,
+  "cross_attn_norm": true,
+  "eps": 1e-06,
+  "vae_stride": [
+    4,
+    8,
+    8
+  ],
+  "vae_z_dim": 16,
+  "dual_model": true,
+  "boundary": 0.875,
+  "sample_shift": 3.0,
+  "sample_steps": 40,
+  "sample_guide_scale": [
+    3.0,
+    4.0
+  ],
+  "num_train_timesteps": 1000,
+  "sample_fps": 16,
+  "frame_num": 81,
+  "sample_neg_prompt": "\u8272\u8c03\u8273\u4e3d\uff0c\u8fc7\u66dd\uff0c\u9759\u6001\uff0c\u7ec6\u8282\u6a21\u7cca\u4e0d\u6e05\uff0c\u5b57\u5e55\uff0c\u98ce\u683c\uff0c\u4f5c\u54c1\uff0c\u753b\u4f5c\uff0c\u753b\u9762\uff0c\u9759\u6b62\uff0c\u6574\u4f53\u53d1\u7070\uff0c\u6700\u5dee\u8d28\u91cf\uff0c\u4f4e\u8d28\u91cf\uff0cJPEG\u538b\u7f29\u6b8b\u7559\uff0c\u4e11\u964b\u7684\uff0c\u6b8b\u7f3a\u7684\uff0c\u591a\u4f59\u7684\u624b\u6307\uff0c\u753b\u5f97\u4e0d\u597d\u7684\u624b\u90e8\uff0c\u753b\u5f97\u4e0d\u597d\u7684\u8138\u90e8\uff0c\u7578\u5f62\u7684\uff0c\u6bc1\u5bb9\u7684\uff0c\u5f62\u6001\u7578\u5f62\u7684\u80a2\u4f53\uff0c\u624b\u6307\u878d\u5408\uff0c\u9759\u6b62\u4e0d\u52a8\u7684\u753b\u9762\uff0c\u6742\u4e71\u7684\u80cc\u666f\uff0c\u4e09\u6761\u817f\uff0c\u80cc\u666f\u4eba\u5f88\u591a\uff0c\u5012\u7740\u8d70",
+  "max_area": 0,
+  "t5_vocab_size": 256384,
+  "t5_dim": 4096,
+  "t5_dim_attn": 4096,
+  "t5_dim_ffn": 10240,
+  "t5_num_heads": 64,
+  "t5_num_layers": 24,
+  "t5_num_buckets": 32,
+  "quantization": {
+    "group_size": 64,
+    "bits": 4
+  }
+}

conversion.json

@@ -0,0 +1,12 @@
+{
+  "source": "ByteDance/Bernini-Diffusers-v2",
+  "source_commit": "399cf6a18a4c523b367b2b1ac25a2a61009e7df3",
+  "dtype": "bfloat16",
+  "converted": "2026-08-18",
+  "components": [
+    "experts",
+    "planner",
+    "t5+vae copied from mlx-community/Bernini-R-bf16 (bit-identical, AB-R-0097)"
+  ],
+  "note": "experts RETRAINED vs Bernini-R (AB-R-0097) -> full reconvert via premap_diffusers_to_wan + mlx-video sanitize, CPU-stream, chunked evals; in-checkpoint fp32 T5 shards 26-31 never downloaded; mllm saved in HF Qwen2.5-VL layout (mllm. prefix stripped); connector/mask_tokens keys verbatim upstream in planner_glue.safetensors"
+}

high_noise_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9bc04f12ccc41bd391aafb2eba772758cd9815a700e77f4487e9aabc4aa40d2
+size 8379507248

low_noise_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bde83f0f550bbcdaec0a35d0f11610fa76ea89ae7b2e10332ecdadf9729e226
+size 8379507248

mllm/chat_template.json

@@ -0,0 +1,3 @@
+{
+    "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

mllm/config.json

@@ -0,0 +1,62 @@
+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "vision_start_token_id": 151652,
+  "vision_end_token_id": 151653,
+  "vision_token_id": 151654,
+  "image_token_id": 151655,
+  "video_token_id": 151656,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 28,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vision_config": {
+    "depth": 32,
+    "hidden_act": "silu",
+    "hidden_size": 1280,
+    "intermediate_size": 3420,
+    "num_heads": 16,
+    "in_chans": 3,
+    "out_hidden_size": 3584,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "window_size": 112,
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "tokens_per_second": 2,
+    "temporal_patch_size": 2,
+    "_attn_implementation": "flash_attention_2"
+  },
+  "rope_scaling": {
+    "type": "mrope",
+    "mrope_section": [
+      16,
+      24,
+      24
+    ]
+  },
+  "vocab_size": 152064
+}

mllm/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 151643,
+  "pad_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "repetition_penalty": 1.05,
+  "temperature": 0.000001,
+  "transformers_version": "4.37.0"
+}

mllm/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c90509813131d6e3db3e5790e4dcbd7cdc8002b9d992206556c114e1e5efd390
+size 16584414354

mllm/preprocessor_config.json

@@ -0,0 +1,19 @@
+{
+  "min_pixels": 3136,
+  "max_pixels": 12845056,
+  "patch_size": 14,
+  "temporal_patch_size": 2,
+  "merge_size": 2,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "processor_class": "Qwen2_5_VLProcessor"
+}

mllm/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "add_bos_token": false
+}

planner_glue.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec57ff5ff05c0cb34c033b2e1dc319a0ee9eb3f3214ba8881c4a84f550756dc4
+size 169399544

t5_encoder.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e86ee4199903e00a88dcd43583a43a6eb898cef600e38670f222d7e37d163787
+size 11361845505

transformer_2_config.json

@@ -0,0 +1,24 @@
+{
+  "_class_name": "WanTransformer3DModel",
+  "_diffusers_version": "0.35.0.dev0",
+  "added_kv_proj_dim": null,
+  "attention_head_dim": 128,
+  "cross_attn_norm": true,
+  "eps": 1e-06,
+  "ffn_dim": 13824,
+  "freq_dim": 256,
+  "image_dim": null,
+  "in_channels": 16,
+  "num_attention_heads": 40,
+  "num_layers": 40,
+  "out_channels": 16,
+  "patch_size": [
+    1,
+    2,
+    2
+  ],
+  "pos_embed_seq_len": null,
+  "qk_norm": "rms_norm_across_heads",
+  "rope_max_seq_len": 1024,
+  "text_dim": 4096
+}

transformer_config.json

@@ -0,0 +1,24 @@
+{
+  "_class_name": "WanTransformer3DModel",
+  "_diffusers_version": "0.35.0.dev0",
+  "added_kv_proj_dim": null,
+  "attention_head_dim": 128,
+  "cross_attn_norm": true,
+  "eps": 1e-06,
+  "ffn_dim": 13824,
+  "freq_dim": 256,
+  "image_dim": null,
+  "in_channels": 16,
+  "num_attention_heads": 40,
+  "num_layers": 40,
+  "out_channels": 16,
+  "patch_size": [
+    1,
+    2,
+    2
+  ],
+  "pos_embed_seq_len": null,
+  "qk_norm": "rms_norm_across_heads",
+  "rope_max_seq_len": 1024,
+  "text_dim": 4096
+}

vae.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:977530e453dbfabbab31e2972e1577d8d7e2840ba7410c81aa3fd421c0cd7414
+size 507591226

vit_decoder.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8895d622e9381cf267f7a22e21d2333491c260891734edc56651821308ee4945
+size 2876184161