Update app.py

app.py

@@ -167,6 +167,15 @@ def generate(prompt,
     downscaled_height, downscaled_width = int(expected_height * downscale_factor), int(expected_width * downscale_factor)
     downscaled_height, downscaled_width = round_to_nearest_resolution_acceptable_by_vae(downscaled_height, downscaled_width)
     
+    timesteps_first_pass = [1000, 993, 987, 981, 975, 909, 725]
+    timesteps_second_pass = [1000, 909, 725, 421]
+    if steps == 8: 
+        timesteps_first_pass = [1000, 993, 987, 981, 975, 909, 725, 0.03]
+        timesteps_second_pass = [1000, 909, 725, 421, 0]
+    elif 7 < steps < 8:
+        timesteps_first_pass = None
+        timesteps_second_pass = None
+    
     latents = pipe(
         conditions=condition1,
         prompt=prompt,
@@ -177,7 +186,7 @@ def generate(prompt,
         num_inference_steps=steps,
         decode_timestep = 0.05,
         decode_noise_scale = 0.025,
-        timesteps=[1000, 993, 987, 981, 975, 909, 725], #[1.0000, 0.9937, 0.9875, 0.9812, 0.9750, 0.9094, 0.7250]
+        timesteps = timesteps_first_pass, #[1.0000, 0.9937, 0.9875, 0.9812, 0.9750, 0.9094, 0.7250]
         image_cond_noise_scale=0.0, # testing
         guidance_rescale=0.7,# testing
         guidance_scale=guidance_scale,
@@ -206,7 +215,7 @@ def generate(prompt,
             num_frames=num_frames,
             guidance_scale=guidance_scale,
             denoise_strength=0.999,  # Effectively, 3 inference steps out of 4
-            timesteps=[1000, 909, 725, 421],
+            timesteps= timesteps_second_pass,
             num_inference_steps=10,
             latents=upscaled_latents,
             decode_timestep=0.05,