Support llava clip vision model.

2025-03-06 00:24:43 -05:00
parent 85ef295069
commit 0bef826a98
4 changed files with 61 additions and 3 deletions
--- a/comfy/clip_vision_config_vitl_336_llava.json
+++ b/comfy/clip_vision_config_vitl_336_llava.json
@@ -0,0 +1,19 @@
+{
+  "attention_dropout": 0.0,
+  "dropout": 0.0,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 1024,
+  "image_size": 336,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-5,
+  "model_type": "clip_vision_model",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 24,
+  "patch_size": 14,
+  "projection_dim": 768,
+  "projector_type": "llava3",
+  "torch_dtype": "float32"
+}