Instructions to use ShimbaLLM/Dupe-R-IMG with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ShimbaLLM/Dupe-R-IMG with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ShimbaLLM/Dupe-R-IMG", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from ShimbaLLM/Dupe-R-IMG: direct link, hf CLI and curl.
- Browser
- Download file 2.15 kB
-
https://huggingface.co/ShimbaLLM/Dupe-R-IMG/resolve/main/config.json
- Command line
-
hf download hf://ShimbaLLM/Dupe-R-IMG/config.json
-
curl -L -o config.json https://huggingface.co/ShimbaLLM/Dupe-R-IMG/resolve/main/config.json
2.15 kB
| { | |
| "model_type": "duper_img", | |
| "repo_id": "ShimbaLLM/Dupe-R-IMG", | |
| "total_params": 297377143, | |
| "n_tensors": 596, | |
| "storage_dtype": "float16", | |
| "compute_dtype": "float32", | |
| "tensor_sections": [ | |
| "dit", | |
| "text_encoder", | |
| "vae" | |
| ], | |
| "section_params": { | |
| "dit": 104094736, | |
| "text_encoder": 109628544, | |
| "vae": 83653863 | |
| }, | |
| "image_size": 256, | |
| "latent_size": 32, | |
| "context_length": 128, | |
| "latent_scaling_factor": 0.18215, | |
| "components": { | |
| "dit": { | |
| "_class_name": "SupraDiT", | |
| "source": "SupraLabs/Supra2-IMG", | |
| "license": "apache-2.0", | |
| "params": 104094736, | |
| "latent_ch": 4, | |
| "latent_size": 32, | |
| "patch": 2, | |
| "d_model": 576, | |
| "depth": 14, | |
| "n_heads": 9, | |
| "mlp_ratio": 4.0, | |
| "ctx_dim": 768, | |
| "max_ctx": 128, | |
| "img_size": 256 | |
| }, | |
| "text_encoder": { | |
| "_class_name": "T5EncoderModel", | |
| "source": "google/flan-t5-base", | |
| "license": "apache-2.0", | |
| "params": 109628544, | |
| "note": "encoder stack only; decoder not bundled", | |
| "d_model": 768, | |
| "num_layers": 12, | |
| "num_heads": 12, | |
| "d_ff": 2048, | |
| "d_kv": 64, | |
| "feed_forward_proj": "gated-gelu", | |
| "vocab_size": 32128, | |
| "n_positions": 512 | |
| }, | |
| "vae": { | |
| "_class_name": "AutoencoderKL", | |
| "source": "stabilityai/sd-vae-ft-mse", | |
| "license": "mit", | |
| "params": 83653863, | |
| "in_channels": 3, | |
| "out_channels": 3, | |
| "latent_channels": 4, | |
| "block_out_channels": [ | |
| 128, | |
| 256, | |
| 512, | |
| 512 | |
| ], | |
| "layers_per_block": 2, | |
| "norm_num_groups": 32, | |
| "act_fn": "silu", | |
| "scaling_factor": 0.18215, | |
| "sample_size": 256 | |
| }, | |
| "sampler": { | |
| "type": "rectified_flow", | |
| "time_range": [ | |
| 0.0, | |
| 1.0 | |
| ], | |
| "default_steps": 50, | |
| "default_cfg_scale": 3.0, | |
| "default_sampler": "euler", | |
| "supports_heun": true | |
| } | |
| }, | |
| "notes": "Repackaging of Supra2-IMG + flan-t5-base (encoder) + sd-vae-ft-mse. Tensors copied unmodified under dit./text_encoder./vae. prefixes; upcast to float32 at load. Not a weight blend." | |
| } | |