StableZero123_Conditioning_Batched node.

This node lets you generate a batch of images with different elevations or
azimuths by setting the elevation_batch_increment and/or
azimuth_batch_increment.

It also sets the batch index for the latents so that the same init noise is
used on each frame.

comfy_extras/nodes_stable3d.py

@@ -53,6 +53,50 @@ class StableZero123_Conditioning:
         latent = torch.zeros([batch_size, 4, height // 8, width // 8])
         return (positive, negative, {"samples":latent})
 
+class StableZero123_Conditioning_Batched:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {"required": { "clip_vision": ("CLIP_VISION",),
+                              "init_image": ("IMAGE",),
+                              "vae": ("VAE",),
+                              "width": ("INT", {"default": 256, "min": 16, "max": nodes.MAX_RESOLUTION, "step": 8}),
+                              "height": ("INT", {"default": 256, "min": 16, "max": nodes.MAX_RESOLUTION, "step": 8}),
+                              "batch_size": ("INT", {"default": 1, "min": 1, "max": 4096}),
+                              "elevation": ("FLOAT", {"default": 0.0, "min": -180.0, "max": 180.0}),
+                              "azimuth": ("FLOAT", {"default": 0.0, "min": -180.0, "max": 180.0}),
+                              "elevation_batch_increment": ("FLOAT", {"default": 0.0, "min": -180.0, "max": 180.0}),
+                              "azimuth_batch_increment": ("FLOAT", {"default": 0.0, "min": -180.0, "max": 180.0}),
+                             }}
+    RETURN_TYPES = ("CONDITIONING", "CONDITIONING", "LATENT")
+    RETURN_NAMES = ("positive", "negative", "latent")
+
+    FUNCTION = "encode"
+
+    CATEGORY = "conditioning/3d_models"
+
+    def encode(self, clip_vision, init_image, vae, width, height, batch_size, elevation, azimuth, elevation_batch_increment, azimuth_batch_increment):
+        output = clip_vision.encode_image(init_image)
+        pooled = output.image_embeds.unsqueeze(0)
+        pixels = comfy.utils.common_upscale(init_image.movedim(-1,1), width, height, "bilinear", "center").movedim(1,-1)
+        encode_pixels = pixels[:,:,:,:3]
+        t = vae.encode(encode_pixels)
+
+        cam_embeds = []
+        for i in range(batch_size):
+            cam_embeds.append(camera_embeddings(elevation, azimuth))
+            elevation += elevation_batch_increment
+            azimuth += azimuth_batch_increment
+
+        cam_embeds = torch.cat(cam_embeds, dim=0)
+        cond = torch.cat([comfy.utils.repeat_to_batch_size(pooled, batch_size), cam_embeds], dim=-1)
+
+        positive = [[cond, {"concat_latent_image": t}]]
+        negative = [[torch.zeros_like(pooled), {"concat_latent_image": torch.zeros_like(t)}]]
+        latent = torch.zeros([batch_size, 4, height // 8, width // 8])
+        return (positive, negative, {"samples":latent, "batch_index": [0] * batch_size})
+
+
 NODE_CLASS_MAPPINGS = {
     "StableZero123_Conditioning": StableZero123_Conditioning,
+    "StableZero123_Conditioning_Batched": StableZero123_Conditioning_Batched,
 }