Instructions to use kandinskylab/tiny-kandinsky-s2v-modular-pipe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use kandinskylab/tiny-kandinsky-s2v-modular-pipe with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("kandinskylab/tiny-kandinsky-s2v-modular-pipe", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Download text_encoder/config.json from kandinskylab/tiny-kandinsky-s2v-modular-pipe: direct link, hf CLI and curl.
- Browser
- Download file 4.4 kB
-
https://huggingface.co/kandinskylab/tiny-kandinsky-s2v-modular-pipe/resolve/main/text_encoder/config.json
- Command line
-
hf download hf://kandinskylab/tiny-kandinsky-s2v-modular-pipe/text_encoder/config.json
-
curl -L -o config.json https://huggingface.co/kandinskylab/tiny-kandinsky-s2v-modular-pipe/resolve/main/text_encoder/config.json
4.4 kB
| { | |
| "_attn_implementation_autoset": true, | |
| "architectures": [ | |
| "Qwen2_5OmniThinkerForConditionalGeneration" | |
| ], | |
| "audio_config": { | |
| "_attn_implementation_autoset": true, | |
| "activation_dropout": 0.0, | |
| "activation_function": "gelu", | |
| "add_cross_attention": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": null, | |
| "cross_attention_hidden_size": null, | |
| "d_model": 16, | |
| "decoder_start_token_id": null, | |
| "dropout": 0.0, | |
| "dtype": "bfloat16", | |
| "encoder_attention_heads": 1, | |
| "encoder_ffn_dim": 32, | |
| "encoder_layerdrop": 0.0, | |
| "encoder_layers": 1, | |
| "eos_token_id": null, | |
| "finetuning_task": null, | |
| "init_std": 0.02, | |
| "initializer_range": 0.02, | |
| "is_decoder": false, | |
| "max_source_positions": 1500, | |
| "model_type": "qwen2_5_omni_audio_encoder", | |
| "n_window": 100, | |
| "num_mel_bins": 128, | |
| "output_dim": 16, | |
| "pad_token_id": null, | |
| "prefix": null, | |
| "pruned_heads": {}, | |
| "scale_embedding": false, | |
| "sep_token_id": null, | |
| "task_specific_params": null, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": null, | |
| "torchscript": false, | |
| "use_bfloat16": false | |
| }, | |
| "audio_end_token_id": 151648, | |
| "audio_start_token_id": 151647, | |
| "audio_token_index": 151646, | |
| "bos_token_id": 151644, | |
| "dtype": "float32", | |
| "eos_token_id": 151645, | |
| "ignore_index": -100, | |
| "image_token_index": 151655, | |
| "init_std": 0.02, | |
| "initializer_range": 0.02, | |
| "model_type": "qwen2_5_omni_thinker", | |
| "pad_token_id": 151643, | |
| "position_id_per_seconds": 25, | |
| "seconds_per_chunk": 2, | |
| "text_config": { | |
| "_attn_implementation_autoset": false, | |
| "add_cross_attention": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": null, | |
| "cross_attention_hidden_size": null, | |
| "decoder_start_token_id": null, | |
| "dtype": "bfloat16", | |
| "eos_token_id": null, | |
| "finetuning_task": null, | |
| "hidden_act": "silu", | |
| "hidden_size": 16, | |
| "init_std": 0.02, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 32, | |
| "is_decoder": false, | |
| "layer_types": [ | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 28, | |
| "model_type": "qwen2_5_omni_text", | |
| "num_attention_heads": 1, | |
| "num_hidden_layers": 1, | |
| "num_key_value_heads": 1, | |
| "pad_token_id": null, | |
| "prefix": null, | |
| "pruned_heads": {}, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "mrope_section": [ | |
| 2, | |
| 2, | |
| 4 | |
| ], | |
| "rope_theta": 1000000.0, | |
| "rope_type": "default", | |
| "type": "default" | |
| }, | |
| "sep_token_id": null, | |
| "sliding_window": null, | |
| "task_specific_params": null, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": false, | |
| "tokenizer_class": null, | |
| "torchscript": false, | |
| "use_bfloat16": false, | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 152064 | |
| }, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.17.0", | |
| "user_token_id": 872, | |
| "video_token_index": 151656, | |
| "vision_config": { | |
| "_attn_implementation_autoset": true, | |
| "add_cross_attention": false, | |
| "bos_token_id": null, | |
| "cross_attention_hidden_size": null, | |
| "decoder_start_token_id": null, | |
| "depth": 2, | |
| "dtype": "bfloat16", | |
| "embed_dim": 16, | |
| "eos_token_id": null, | |
| "finetuning_task": null, | |
| "fullatt_block_indexes": [ | |
| 1 | |
| ], | |
| "hidden_act": "silu", | |
| "hidden_size": 16, | |
| "in_channels": 3, | |
| "in_chans": 3, | |
| "init_std": 0.02, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 32, | |
| "is_decoder": false, | |
| "model_type": "qwen2_5_omni_vision_encoder", | |
| "num_heads": 1, | |
| "out_hidden_size": 16, | |
| "pad_token_id": null, | |
| "patch_size": 14, | |
| "prefix": null, | |
| "pruned_heads": {}, | |
| "rope_parameters": { | |
| "rope_theta": 10000.0, | |
| "rope_type": "axial" | |
| }, | |
| "sep_token_id": null, | |
| "spatial_merge_size": 2, | |
| "spatial_patch_size": 14, | |
| "task_specific_params": null, | |
| "temporal_patch_size": 2, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": null, | |
| "tokens_per_second": 25, | |
| "torchscript": false, | |
| "use_bfloat16": false, | |
| "window_size": 112 | |
| }, | |
| "vision_end_token_id": 151653, | |
| "vision_start_token_id": 151652, | |
| "vision_token_id": 151654 | |
| } | |