Image-to-Image
Transformers
Safetensors
in-image-machine-translation
image-translation
image-editing
multimodal
qwen2.5-vl
flux
Instructions to use SeerRay-Lab/Unitranslator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SeerRay-Lab/Unitranslator with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-image" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("image-to-image", model="SeerRay-Lab/Unitranslator")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("SeerRay-Lab/Unitranslator", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download univa/config.json from SeerRay-Lab/Unitranslator: direct link, hf CLI and curl.
- Browser
- Download file 2.88 kB
-
https://huggingface.co/SeerRay-Lab/Unitranslator/resolve/main/univa/config.json
- Command line
-
hf download hf://SeerRay-Lab/Unitranslator/univa/config.json
-
curl -L -o config.json https://huggingface.co/SeerRay-Lab/Unitranslator/resolve/main/univa/config.json
2.88 kB
| { | |
| "architectures": [ | |
| "MaskTFUnivaQwen2p5VLForConditionalGeneration" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "denoise_tower": { | |
| "denoise_projector_type": "mlp2x_gelu", | |
| "denoiser_config": { | |
| "_class_name": "FluxTransformer2DModel", | |
| "_diffusers_version": "0.34.0.dev0", | |
| "_name_or_path": "../checkpoints/flux-dev/transformer", | |
| "attention_head_dim": 128, | |
| "axes_dims_rope": [ | |
| 16, | |
| 56, | |
| 56 | |
| ], | |
| "guidance_embeds": true, | |
| "in_channels": 64, | |
| "joint_attention_dim": 4096, | |
| "num_attention_heads": 24, | |
| "num_layers": 19, | |
| "num_single_layers": 38, | |
| "out_channels": null, | |
| "patch_size": 1, | |
| "pooled_projection_dim": 768 | |
| }, | |
| "denoiser_type": "flux", | |
| "fusion_layer_ff_dim_mult": 4, | |
| "fusion_layer_num_heads": 16, | |
| "input_hidden_size": 2048, | |
| "model_type": "univa_denoise_tower", | |
| "output_hidden_size": 4096 | |
| }, | |
| "eos_token_id": 151645, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "image_begin_token_id": 151652, | |
| "image_end_token_id": 151653, | |
| "image_token_id": 151655, | |
| "image_token_length": null, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 11008, | |
| "mask_tower_config": { | |
| "input_hidden_size": 2048, | |
| "intermediate_channels": [ | |
| 1280, | |
| 640, | |
| 320 | |
| ], | |
| "mgm_dev_convs_nums": 4, | |
| "mgm_head_num": 8, | |
| "mgm_hidden_size": 768, | |
| "mgm_layer_num": 2, | |
| "model_type": "univa_mask_tower", | |
| "output_channels": 1, | |
| "torch_dtype": "float16", | |
| "upsample_scale": 16 | |
| }, | |
| "max_position_embeddings": 128000, | |
| "max_window_layers": 70, | |
| "model_type": "univa_qwen2p5vl", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 36, | |
| "num_key_value_heads": 2, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "mrope_section": [ | |
| 16, | |
| 24, | |
| 24 | |
| ], | |
| "rope_type": "default", | |
| "type": "default" | |
| }, | |
| "rope_theta": 1000000.0, | |
| "shortcut_image_embeds": false, | |
| "shortcut_image_embeds_scale": 0.5, | |
| "shortcut_projector_type": null, | |
| "sliding_window": 32768, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.50.0", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "video_token_id": 151656, | |
| "vision_config": { | |
| "depth": 32, | |
| "fullatt_block_indexes": [ | |
| 7, | |
| 15, | |
| 23, | |
| 31 | |
| ], | |
| "hidden_act": "silu", | |
| "hidden_size": 1280, | |
| "in_channels": 3, | |
| "in_chans": 3, | |
| "intermediate_size": 3420, | |
| "model_type": "qwen2_5_vl", | |
| "num_heads": 16, | |
| "out_hidden_size": 2048, | |
| "patch_size": 14, | |
| "spatial_merge_size": 2, | |
| "spatial_patch_size": 14, | |
| "temporal_patch_size": 2, | |
| "tokens_per_second": 2, | |
| "torch_dtype": "float16", | |
| "window_size": 112 | |
| }, | |
| "vision_end_token_id": 151653, | |
| "vision_start_token_id": 151652, | |
| "vision_token_id": 151654, | |
| "vocab_size": 151936 | |
| } | |