Duplicate from mit-han-lab/foreact-pretrained

Co-authored-by: Zhuoyang Zhang <zhuoyang20@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+trainer_state.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,28 @@
+{
+  "_gradient_checkpointing": false,
+  "architectures": [
+    "VisualForesight"
+  ],
+  "attn_implementation": null,
+  "diffusion_model_id": "Efficient-Large-Model/Sana_1600M_512px_diffusers",
+  "dtype": "bfloat16",
+  "in_channels": 32,
+  "input_size": [
+    15,
+    20
+  ],
+  "max_input_text_tokens": 256,
+  "mllm_id": "google/gemma-2-2b-it",
+  "model_type": "visualforesight",
+  "modules_to_freeze": [
+    "vae",
+    "mllm_backbone"
+  ],
+  "modules_to_unfreeze": [],
+  "noise_scheduler_id": "Efficient-Large-Model/Sana_1600M_512px_diffusers",
+  "scheduler_id": "Efficient-Large-Model/Sana_1600M_512px_diffusers",
+  "system_prompt": "You are a robot and should focus on your actions. Generate a new image that meets the user's instruction while maintaining consistency with the original input where appropriate.",
+  "transformers_version": "4.57.1",
+  "vae_downsample_f": 32,
+  "vae_id": "Efficient-Large-Model/Sana_1600M_512px_diffusers"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4d5fd396dea2b11f3ba1220232ac2148069ddfcd26773dcc29585c0a4fee0f7
+size 4988029512

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:735169436251e2fb0876ec54085828bf178b87ef70c8a2d0a2c4b9b63a537f95
+size 4999982648

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b508be211e31684541f48733a991ed6cebdd7022f0d4097c62c2f10749970e2
+size 253880534