No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from inclusionAI/Ming-flash-omni-2.0
All models by inclusionAI →
📑 Technical Report｜🤗 Hugging Face｜ 🤖 ModelScope
The newly released Ming-flash-omni 2.0 leverages the Ling-2.0 architecture—a Mixture-of-Experts (MoE) framework comprising 100B total and 6B active parameters. Representing a generational advancement over its predecessor, it establishes new State-of-the-Art (SOTA) benchmarks among open-source omni-MLLMs. Ming-flash-omni 2.0 effectively synergizes foundational abilities with specialized domain expertise. In particular, it exhibits superior performance in visual encyclopedic knowledge, immersive speech synthesis, and high-dynamic image generation and manipulation.
Compared to Ming-flash-omni Preview, Ming-flash-omni 2.0 focuses on optimizing capabilities across the following key domains:
Expert-level Multimodal Cognition: It accurately identifies plants and animals, recognizing cultural references (from regional cuisines to global landmarks), and delivering expert-level analysis of artifacts, including era, form, and craftsmanship. By synergizing high-resolution visual capture with a vast knowledge graph, the model achieves "vision-to-knowledge" synthesis, enabling superior knowledge understanding.
Immersive and Controllable Unified Acoustic Synthesis: Ming-flash-omni 2.0 introduces a unified end-to-end acoustic generation pipeline that integrates Speech, Audio, and Music within a single channel. Leveraging Continuous Autoregression coupled with a Diffusion Transformer (DiT) head, the model enables zero-shot voice cloning and nuanced attribute control (e.g., emotion, timbre, and ambient atmosphere). This architecture facilitates a transition from simple text-to-speech to highly expressive, emotionally resonant, and immersive auditory experiences.
High-Dynamic Controllable Image Generation and Manipulation: Ming-flash-omni 2.0 features a native multi-task architecture that unifies segmentation, generation, and editing, allowing for sophisticated spatiotemporal semantic decoupling. It excels in high-dynamic content creation, including atmospheric reconstruction, seamless scene composition, and context-aware object removal. By maintaining texture coherence and spatial depth consistency, Ming-flash-omni 2.0 achieves state-of-the-art precision in complex image manipulation tasks.
You can download our latest model from both Huggingface and ModelScope. For previous version model like Ming-flash-omni-Preview, Please refer to this link.
Note: This download process will take several minutes to several hours, depending on your network conditions.
We provide a step-by-step running example:
Step 1 - Download the source code
Step 2 - Download the model weights and create a soft link to the source code directory
Download our model following Model Downloads
Step 3 - Enter the code directory, you can refer to the following codes to run the Ming-flash-omni model.
We also provide a simple example on the usage of this repo. For detailed usage, please refer to cookbook.ipynb.
If you find our work helpful, feel free to give us a cite.
pip install modelscopemodelscope download --model inclusionAI/Ming-flash-omni-2.0 --local_dir inclusionAI/Ming-flash-omni-2.0 --revision masterpip install -r requirements.txtpip install nvidia-cublas-cu12==12.4.5.8 # for H20 GPUgit clone https://github.com/inclusionAI/Ming.git cd Mingmkdir inclusionAI ln -s /path/to/inclusionAI/Ming-flash-omni-2.0 inclusionAI/Ming-flash-omni-2.0jupyter notebook cookbook.ipynbimport osimport torchimport warningsfrom bisect import bisect_leftwarnings.filterwarnings("ignore")
from transformers import AutoProcessorfrom modeling_bailingmm2 import BailingMM2NativeForConditionalGeneration
def split_model(): device_map = {} world_size = torch.cuda.device_count() num_layers = 32 layer_per_gpu = num_layers // world_size layer_per_gpu = [i * layer_per_gpu for i in range(1, world_size + 1)] for i in range(num_layers): device_map[f'model.model.layers.{i}'] = bisect_left(layer_per_gpu, i) device_map['vision'] = 0 device_map['audio'] = 0 device_map['linear_proj'] = 0 device_map['linear_proj_audio'] = 0 device_map['model.model.word_embeddings.weight'] = 0 device_map['model.model.norm.weight'] = 0 device_map['model.lm_head.weight'] = 0 device_map['model.model.norm'] = 0 device_map[f'model.model.layers.{num_layers - 1}'] = 0 return device_map
# Load pre-trained model with optimized settings, this will take ~10 minutesmodel_path = "inclusionAI/Ming-flash-omni-2.0"model = BailingMM2NativeForConditionalGeneration.from_pretrained( model_path, torch_dtype=torch.bfloat16, attn_implementation="flash_attention_2", device_map=split_model(), load_image_gen=True, load_talker=True,).to(dtype=torch.bfloat16)
# Initialize processor for handling multimodal inputsprocessor = AutoProcessor.from_pretrained(model_path, trust_remote_code=True)
# Inference Pipelinedef generate(messages, processor, model, sys_prompt_exp=None, use_cot_system_prompt=False, max_new_tokens=512): text = processor.apply_chat_template( messages, sys_prompt_exp=sys_prompt_exp, use_cot_system_prompt=use_cot_system_prompt ) image_inputs, video_inputs, audio_inputs = processor.process_vision_info(messages)
inputs = processor( text=[text], images=image_inputs, videos=video_inputs, audios=audio_inputs, return_tensors="pt", audio_kwargs={"use_whisper_encoder": True}, ).to(model.device)
for k in inputs.keys(): if k == "pixel_values" or k == "pixel_values_videos" or k == "audio_feats": inputs[k] = inputs[k].to(dtype=torch.bfloat16)
with torch.no_grad(): generated_ids = model.generate( **inputs, max_new_tokens=max_new_tokens, use_cache=True, eos_token_id=processor.gen_terminator, num_logits_to_keep=1, )
generated_ids_trimmed = [ out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids) ]
output_text = processor.batch_decode( generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False )[0]
return output_text
# qamessages = [ { "role": "HUMAN", "content": [ {"type": "text", "text": "请详细介绍鹦鹉的生活习性。"} ], },]output_text = generate(messages, processor=processor, model=model)print(output_text)# Output:
# 鹦鹉是一种非常受欢迎的宠物鸟类，它们以其鲜艳的羽毛、聪明的头脑和模仿人类语言的能力而闻名。鹦鹉的生活习性非常丰富，以下是一些主要的习性：
# 1. **社交性**：鹦鹉是高度社交的鸟类，它们在野外通常生活在群体中，与同伴互动、玩耍和寻找食物。在家庭环境中，鹦鹉需要与人类或其他鹦鹉进行定期的互动，以保持其心理健康。
# 2. **智力**：鹦鹉拥有非常高的智力，它们能够学习各种技能，包括模仿人类语言、识别物体、解决问题等。这种智力使它们成为非常有趣的宠物。
# ......
@misc{Mingomni2025, title = {Ming-Omni: A Unified Multimodal Model for Perception and Generation}, author = {Inclusion AI}, year = {2025}, eprint = {2506.09344}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.09344}}
@article{ai2025ming, title={Ming-flash-omni: A sparse, unified architecture for multimodal perception and generation}, author={Inclusion AI}, journal={arXiv preprint arXiv:2510.24821}, year={2025}}