Add support for unCLIP SD2.x models.

See _for_testing/unclip in the UI for the new nodes.

unCLIPCheckpointLoader is used to load them.

unCLIPConditioning is used to add the image cond and takes as input a
CLIPVisionEncode output which has been moved to the conditioning section.

comfy/ldm/models/diffusion/dpm_solver/dpm_solver.py

@@ -307,7 +307,16 @@ def model_wrapper(
             else:
                 x_in = torch.cat([x] * 2)
                 t_in = torch.cat([t_continuous] * 2)
-                c_in = torch.cat([unconditional_condition, condition])
+                if isinstance(condition, dict):
+                    assert isinstance(unconditional_condition, dict)
+                    c_in = dict()
+                    for k in condition:
+                        if isinstance(condition[k], list):
+                            c_in[k] = [torch.cat([unconditional_condition[k][i], condition[k][i]]) for i in range(len(condition[k]))]
+                        else:
+                            c_in[k] = torch.cat([unconditional_condition[k], condition[k]])
+                else:
+                    c_in = torch.cat([unconditional_condition, condition])
                 noise_uncond, noise = noise_pred_fn(x_in, t_in, cond=c_in).chunk(2)
                 return noise_uncond + guidance_scale * (noise - noise_uncond)