Revert "Add pre-generation conditioning ascent to value function guidance"

This reverts commit 1283203c648129bcbed2274db93f078d5427c6f5.

samplers.py

@@ -1467,11 +1467,7 @@ class FunPackLTXAVSceneChainSampler:
                 print("[FunPackSceneChain] embed_guidance: no liked direction found (need 3+ liked generations)")
             else:
                 _value_fn = self._load_value_function(refinement_key_input)
-                if _value_fn:
-                    ready = _value_fn.is_ready()
-                    mode = f"value function ({_value_fn.n_trained} samples, ascent {'on' if ready else 'pending'})"
-                else:
-                    mode = "fixed direction"
+                mode = f"value function ({_value_fn.n_trained} samples)" if _value_fn else "fixed direction"
                 print(f"[FunPackSceneChain] embed_guidance: active via {mode}, strength={embed_guidance_strength}")
 
         first_scene_seed = self._scene_seed(scene_conditionings[0])
@@ -1517,10 +1513,6 @@ class FunPackLTXAVSceneChainSampler:
                 else:
                     guide_tail = 0
 
-            if embed_guidance and _value_fn is not None and _value_fn.is_ready():
-                orig_cond, orig_extra = scene_positive[0][0], scene_positive[0][1]
-                ascended = _value_fn.ascend(orig_cond)
-                scene_positive = [[ascended, orig_extra]] + list(scene_positive[1:])
             if embed_guidance and _liked_dir is not None:
                 _eg_old_wrapper = self._build_embed_guidance_wrapper(model, _liked_dir, embed_guidance_strength, value_fn=_value_fn)
             sampled = self._sample_chunk(

value_function.py

@@ -85,30 +85,6 @@ class OnlineValueFunction(nn.Module):
             reward.backward()
         return c_fresh.grad.to(orig_device, conditioning.dtype)
 
-    def ascend(self, conditioning):
-        """Gradient ascent on conditioning until reward plateaus. Self-terminating, no user params."""
-        if not self.is_ready():
-            return conditioning
-        mlp_device = next(self.parameters()).device
-        orig_device = conditioning.device
-        orig_dtype = conditioning.dtype
-        step_size = conditioning.float().norm().item() * 0.005
-        prev_reward = -float("inf")
-        with torch.inference_mode(False), torch.enable_grad():
-            c = torch.empty(conditioning.shape, dtype=torch.float32, device=mlp_device)
-            c.copy_(conditioning)
-            for _ in range(50):
-                c = c.detach().requires_grad_(True)
-                reward = self.forward(self.compress(c).unsqueeze(0))
-                reward.backward()
-                reward_val = reward.item()
-                grad = F.normalize(c.grad.float(), dim=-1)
-                c = c.detach() + step_size * grad
-                if reward_val - prev_reward < 1e-3:
-                    break
-                prev_reward = reward_val
-        return c.detach().to(orig_device, orig_dtype)
-
     def is_ready(self):
         return len(self.buffer_c) >= self.MIN_SAMPLES