API tools faq
paste
Advertisement
Guest User

Untitled

a guest
Jun 14th, 2025
12
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 25.41 KB | None | 0 0
raw download clone embed print report
  1. INFO: Detail Daemon is enabled
  2. 🔍 RAW ARGS DEBUG: preserve_dc_component_v2=False, use_correct_fft_shift=False, mask_function=corner_average
  3. 🔍 Frequency Separation: process() called - enabled=True, p_type=StableDiffusionProcessingTxt2Img
  4. 🎨 Frequency Separation: txt2img mode detected - will enhance after generation
  5. 📊 Using custom steps/cfg: False
  6. 📊 Using generation settings: steps=30, cfg=7
  7. 100%|██████████| 30/30 [00:03<00:00, 9.32it/s]
  8. [Tiled VAE]: the input size is tiny and unnecessary to tile.
  9.  
  10. 🎨 Frequency Separation: Processing batch 0 before ADetailer...
  11. 📊 Batch contains 1 images, shape: torch.Size([1, 3, 512, 512])
  12.  
  13. 🖼️ Processing image 1/1...
  14. 🔧 Using recombination method: frequency_reconstruction
  15. 💾 Save before denoising: True
  16. 💡 Preserve DC component: False
  17. 🔧 FFT Shift: False
  18. 🎯 FFT Shift Detail Inspection: False
  19. 🎭 Mask Function: corner_average
  20. 🔍 DEBUG: preserve_dc_component=False, use_fft_shift=False, use_correct_fft_shift=False, mask_function=corner_average
  21. 🧠 Processing 1 images with REAL DIFFUSION in latent space
  22. 🌊 Sync Mode: progressive_refinement
  23. 🖼️ Frequency Bands: 3
  24. 🏢 Band Configuration: low_freq(0.00-0.15, denoise:0.30, steps:30), mid_freq(0.10-0.40, denoise:0.30, steps:30), high_freq(0.35-1.00, denoise:0.30, steps:30)
  25.  
  26. 🎯 ==> Processing image 1/1 with REAL DIFFUSION...
  27. 🔄 Step 1: Encoding image to latent space...
  28. [Tiled VAE]: the input size is tiny and unnecessary to tile.
  29. 📐 Successfully encoded image to latent: torch.Size([1, 8, 64, 64])
  30. ✅ Encoded to latent shape: torch.Size([1, 8, 64, 64])
  31. 📊 Original latent stats: mean=-1.668, std=1.691, range=[-11.922, 8.297]
  32. 🔋 Input latent energy: 5.645 (reference for normalization)
  33. 🌊 Step 2: Splitting into frequency bands...
  34. 📊 Using CORNER AVERAGE distance calculation
  35. 🎵 low_freq: (0, 0.15) -> torch.Size([1, 8, 64, 64])
  36. 📊 Stats: mean=0.000, std=0.131, max=0.936
  37. 📊 Using CORNER AVERAGE distance calculation
  38. 🎵 mid_freq: (0.1, 0.4) -> torch.Size([1, 8, 64, 64])
  39. 📊 Stats: mean=0.000, std=0.182, max=2.516
  40. 📊 Using CORNER AVERAGE distance calculation
  41. 🎵 high_freq: (0.35, 1) -> torch.Size([1, 8, 64, 64])
  42. 📊 Stats: mean=-0.834, std=0.940, max=8.008
  43. ✅ Split into 3 frequency bands
  44. 🔥 Step 3: Running REAL DIFFUSION on each frequency band...
  45. ⚠️ This will take time and show progress bars for each band!
  46. 📈 Added 3 frequency band diffusion jobs to queue
  47. 🎛️ REAL DIFFUSION processing low_freq band (denoising: 0.3, steps: 30, cfg: 7)
  48. 📊 Band config: steps=30, cfg=7
  49. 🔥 Starting REAL diffusion on low_freq band...
  50. ⚠️ Error decoding latent to image: Given groups=1, weight of size [4, 4, 1, 1], expected input[1, 8, 64, 64] to have 4 channels, but got 8 channels instead
  51. Traceback (most recent call last):
  52. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\extensions\sd-webui-frequency-separation\scripts\frequency_separation.py", line 1303, in decode_latent_to_image
  53. decoded = p.sd_model.decode_first_stage(latent_for_decode)
  54. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\modules\sd_hijack_utils.py", line 22, in <lambda>
  55. setattr(resolved_obj, func_path[-1], lambda *args, **kwargs: self(*args, **kwargs))
  56. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\modules\sd_hijack_utils.py", line 36, in __call__
  57. return self.__orig_func(*args, **kwargs)
  58. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\venv\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
  59. return func(*args, **kwargs)
  60. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 826, in decode_first_stage
  61. return self.first_stage_model.decode(z)
  62. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\modules\lowvram.py", line 74, in first_stage_model_decode_wrap
  63. return first_stage_model_decode(z)
  64. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\repositories\stable-diffusion-stability-ai\ldm\models\autoencoder.py", line 89, in decode
  65. z = self.post_quant_conv(z)
  66. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\venv\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
  67. return self._call_impl(*args, **kwargs)
  68. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\venv\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
  69. return forward_call(*args, **kwargs)
  70. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\extensions-builtin\Lora\networks.py", line 599, in network_Conv2d_forward
  71. return originals.Conv2d_forward(self, input)
  72. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\venv\lib\site-packages\torch\nn\modules\conv.py", line 460, in forward
  73. return self._conv_forward(input, self.weight, self.bias)
  74. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\venv\lib\site-packages\torch\nn\modules\conv.py", line 456, in _conv_forward
  75. return F.conv2d(input, weight, bias, self.stride,
  76. RuntimeError: Given groups=1, weight of size [4, 4, 1, 1], expected input[1, 8, 64, 64] to have 4 channels, but got 8 channels instead
  77. 🔄 Created fallback image: (512, 512)
  78. 🖼️ Decoded low_freq band to image: (512, 512)
  79. 🔧 Copied scripts from base processing: 379 script args
  80. ⚙️ Running diffusion: 30 steps, denoising 0.30, CFG 7, seed -1
  81. 🔧 Processing object ready: scripts=True, script_args=379
  82. 🚀 Starting processing.process_images() for low_freq...
  83. INFO: Detail Daemon is enabled
  84. 🔍 RAW ARGS DEBUG: preserve_dc_component_v2=False, use_correct_fft_shift=False, mask_function=corner_average
  85. 🔍 Frequency Separation: process() called - enabled=True, p_type=StableDiffusionProcessingImg2Img
  86. 🔄 Frequency Separation: Disabled for internal frequency band processing, skipping
  87. [Tiled VAE]: the input size is tiny and unnecessary to tile.
  88. 100%|██████████| 10/10 [00:01<00:00, 9.14it/s]
  89. [Tiled VAE]: the input size is tiny and unnecessary to tile.
  90. ✅ process_images() completed for low_freq
  91. 📐 Successfully encoded image to latent: torch.Size([1, 8, 64, 64])
  92. ✅ low_freq diffusion complete! Shape: torch.Size([1, 8, 64, 64])
  93. ✅ low_freq band REAL diffusion complete
  94. 🎛️ REAL DIFFUSION processing mid_freq band (denoising: 0.3, steps: 30, cfg: 7)
  95. 📊 Band config: steps=30, cfg=7
  96. 🔥 Starting REAL diffusion on mid_freq band...
  97. ⚠️ Error decoding latent to image: Given groups=1, weight of size [4, 4, 1, 1], expected input[1, 8, 64, 64] to have 4 channels, but got 8 channels instead
  98. Traceback (most recent call last):
  99. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\extensions\sd-webui-frequency-separation\scripts\frequency_separation.py", line 1303, in decode_latent_to_image
  100. decoded = p.sd_model.decode_first_stage(latent_for_decode)
  101. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\modules\sd_hijack_utils.py", line 22, in <lambda>
  102. setattr(resolved_obj, func_path[-1], lambda *args, **kwargs: self(*args, **kwargs))
  103. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\modules\sd_hijack_utils.py", line 36, in __call__
  104. return self.__orig_func(*args, **kwargs)
  105. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\venv\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
  106. return func(*args, **kwargs)
  107. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 826, in decode_first_stage
  108. return self.first_stage_model.decode(z)
  109. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\modules\lowvram.py", line 74, in first_stage_model_decode_wrap
  110. return first_stage_model_decode(z)
  111. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\repositories\stable-diffusion-stability-ai\ldm\models\autoencoder.py", line 89, in decode
  112. z = self.post_quant_conv(z)
  113. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\venv\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
  114. return self._call_impl(*args, **kwargs)
  115. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\venv\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
  116. return forward_call(*args, **kwargs)
  117. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\extensions-builtin\Lora\networks.py", line 599, in network_Conv2d_forward
  118. return originals.Conv2d_forward(self, input)
  119. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\venv\lib\site-packages\torch\nn\modules\conv.py", line 460, in forward
  120. return self._conv_forward(input, self.weight, self.bias)
  121. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\venv\lib\site-packages\torch\nn\modules\conv.py", line 456, in _conv_forward
  122. return F.conv2d(input, weight, bias, self.stride,
  123. RuntimeError: Given groups=1, weight of size [4, 4, 1, 1], expected input[1, 8, 64, 64] to have 4 channels, but got 8 channels instead
  124. 🔄 Created fallback image: (512, 512)
  125. 🖼️ Decoded mid_freq band to image: (512, 512)
  126. 🔧 Copied scripts from base processing: 379 script args
  127. ⚙️ Running diffusion: 30 steps, denoising 0.30, CFG 7, seed -1
  128. 🔧 Processing object ready: scripts=True, script_args=379
  129. 🚀 Starting processing.process_images() for mid_freq...
  130. INFO: Detail Daemon is enabled
  131. 🔍 RAW ARGS DEBUG: preserve_dc_component_v2=False, use_correct_fft_shift=False, mask_function=corner_average
  132. 🔍 Frequency Separation: process() called - enabled=True, p_type=StableDiffusionProcessingImg2Img
  133. 🔄 Frequency Separation: Disabled for internal frequency band processing, skipping
  134. [Tiled VAE]: the input size is tiny and unnecessary to tile.
  135. 100%|██████████| 10/10 [00:01<00:00, 9.09it/s]
  136. [Tiled VAE]: the input size is tiny and unnecessary to tile.
  137. ✅ process_images() completed for mid_freq
  138. 📐 Successfully encoded image to latent: torch.Size([1, 8, 64, 64])
  139. ✅ mid_freq diffusion complete! Shape: torch.Size([1, 8, 64, 64])
  140. ✅ mid_freq band REAL diffusion complete
  141. 🎛️ REAL DIFFUSION processing high_freq band (denoising: 0.3, steps: 30, cfg: 7)
  142. 📊 Band config: steps=30, cfg=7
  143. 🔥 Starting REAL diffusion on high_freq band...
  144. ⚠️ Error decoding latent to image: Given groups=1, weight of size [4, 4, 1, 1], expected input[1, 8, 64, 64] to have 4 channels, but got 8 channels instead
  145. Traceback (most recent call last):
  146. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\extensions\sd-webui-frequency-separation\scripts\frequency_separation.py", line 1303, in decode_latent_to_image
  147. decoded = p.sd_model.decode_first_stage(latent_for_decode)
  148. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\modules\sd_hijack_utils.py", line 22, in <lambda>
  149. setattr(resolved_obj, func_path[-1], lambda *args, **kwargs: self(*args, **kwargs))
  150. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\modules\sd_hijack_utils.py", line 36, in __call__
  151. return self.__orig_func(*args, **kwargs)
  152. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\venv\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
  153. return func(*args, **kwargs)
  154. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 826, in decode_first_stage
  155. return self.first_stage_model.decode(z)
  156. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\modules\lowvram.py", line 74, in first_stage_model_decode_wrap
  157. return first_stage_model_decode(z)
  158. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\repositories\stable-diffusion-stability-ai\ldm\models\autoencoder.py", line 89, in decode
  159. z = self.post_quant_conv(z)
  160. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\venv\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
  161. return self._call_impl(*args, **kwargs)
  162. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\venv\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
  163. return forward_call(*args, **kwargs)
  164. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\extensions-builtin\Lora\networks.py", line 599, in network_Conv2d_forward
  165. return originals.Conv2d_forward(self, input)
  166. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\venv\lib\site-packages\torch\nn\modules\conv.py", line 460, in forward
  167. return self._conv_forward(input, self.weight, self.bias)
  168. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\venv\lib\site-packages\torch\nn\modules\conv.py", line 456, in _conv_forward
  169. return F.conv2d(input, weight, bias, self.stride,
  170. RuntimeError: Given groups=1, weight of size [4, 4, 1, 1], expected input[1, 8, 64, 64] to have 4 channels, but got 8 channels instead
  171. 🔄 Created fallback image: (512, 512)
  172. 🖼️ Decoded high_freq band to image: (512, 512)
  173. 🔧 Copied scripts from base processing: 379 script args
  174. ⚙️ Running diffusion: 30 steps, denoising 0.30, CFG 7, seed -1
  175. 🔧 Processing object ready: scripts=True, script_args=379
  176. 🚀 Starting processing.process_images() for high_freq...
  177. INFO: Detail Daemon is enabled
  178. 🔍 RAW ARGS DEBUG: preserve_dc_component_v2=False, use_correct_fft_shift=False, mask_function=corner_average
  179. 🔍 Frequency Separation: process() called - enabled=True, p_type=StableDiffusionProcessingImg2Img
  180. 🔄 Frequency Separation: Disabled for internal frequency band processing, skipping
  181. [Tiled VAE]: the input size is tiny and unnecessary to tile.
  182. 100%|██████████| 10/10 [00:01<00:00, 9.27it/s]
  183. [Tiled VAE]: the input size is tiny and unnecessary to tile.
  184. ✅ process_images() completed for high_freq
  185. 📐 Successfully encoded image to latent: torch.Size([1, 8, 64, 64])
  186. ✅ high_freq diffusion complete! Shape: torch.Size([1, 8, 64, 64])
  187. ✅ high_freq band REAL diffusion complete
  188. 🎆 All frequency bands processed! 3/3 successful
  189. 📊 low_freq processed latent: mean=-1.925, std=2.029
  190. 📊 mid_freq processed latent: mean=-1.951, std=2.055
  191. 📊 high_freq processed latent: mean=-1.942, std=2.047
  192. 📊 Average processed latent: mean=-1.939, std=2.044
  193. 🔍 Mean change: -1.668 → -1.939 (diff: -0.271)
  194. 🔍 Std change: 1.691 → 2.044 (diff: 0.352)
  195. ⚡ Step 3.5: Latent space energy normalization...
  196. 🔋 low_freq latent energy: 7.820
  197. 🔋 mid_freq latent energy: 8.031
  198. 🔋 high_freq latent energy: 7.961
  199. 🔋 Total processed latent energy: 23.812
  200. 🔋 Input latent energy (reference): 5.645
  201. 🎨 Step 4: Multi-VAE decoding each frequency band separately...
  202. 🖼️ VAE decoding low_freq band...
  203. ⚠️ Error decoding latent to image: Given groups=1, weight of size [4, 4, 1, 1], expected input[1, 8, 64, 64] to have 4 channels, but got 8 channels instead
  204. Traceback (most recent call last):
  205. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\extensions\sd-webui-frequency-separation\scripts\frequency_separation.py", line 1303, in decode_latent_to_image
  206. decoded = p.sd_model.decode_first_stage(latent_for_decode)
  207. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\modules\sd_hijack_utils.py", line 22, in <lambda>
  208. setattr(resolved_obj, func_path[-1], lambda *args, **kwargs: self(*args, **kwargs))
  209. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\modules\sd_hijack_utils.py", line 36, in __call__
  210. return self.__orig_func(*args, **kwargs)
  211. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\venv\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
  212. return func(*args, **kwargs)
  213. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 826, in decode_first_stage
  214. return self.first_stage_model.decode(z)
  215. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\modules\lowvram.py", line 74, in first_stage_model_decode_wrap
  216. return first_stage_model_decode(z)
  217. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\repositories\stable-diffusion-stability-ai\ldm\models\autoencoder.py", line 89, in decode
  218. z = self.post_quant_conv(z)
  219. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\venv\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
  220. return self._call_impl(*args, **kwargs)
  221. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\venv\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
  222. return forward_call(*args, **kwargs)
  223. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\extensions-builtin\Lora\networks.py", line 599, in network_Conv2d_forward
  224. return originals.Conv2d_forward(self, input)
  225. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\venv\lib\site-packages\torch\nn\modules\conv.py", line 460, in forward
  226. return self._conv_forward(input, self.weight, self.bias)
  227. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\venv\lib\site-packages\torch\nn\modules\conv.py", line 456, in _conv_forward
  228. return F.conv2d(input, weight, bias, self.stride,
  229. RuntimeError: Given groups=1, weight of size [4, 4, 1, 1], expected input[1, 8, 64, 64] to have 4 channels, but got 8 channels instead
  230. 🔄 Created fallback image: (512, 512)
  231. ✅ low_freq band decoded: (512, 512)
  232. 🖼️ VAE decoding mid_freq band...
  233. ⚠️ Error decoding latent to image: Given groups=1, weight of size [4, 4, 1, 1], expected input[1, 8, 64, 64] to have 4 channels, but got 8 channels instead
  234. Traceback (most recent call last):
  235. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\extensions\sd-webui-frequency-separation\scripts\frequency_separation.py", line 1303, in decode_latent_to_image
  236. decoded = p.sd_model.decode_first_stage(latent_for_decode)
  237. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\modules\sd_hijack_utils.py", line 22, in <lambda>
  238. setattr(resolved_obj, func_path[-1], lambda *args, **kwargs: self(*args, **kwargs))
  239. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\modules\sd_hijack_utils.py", line 36, in __call__
  240. return self.__orig_func(*args, **kwargs)
  241. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\venv\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
  242. return func(*args, **kwargs)
  243. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 826, in decode_first_stage
  244. return self.first_stage_model.decode(z)
  245. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\modules\lowvram.py", line 74, in first_stage_model_decode_wrap
  246. return first_stage_model_decode(z)
  247. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\repositories\stable-diffusion-stability-ai\ldm\models\autoencoder.py", line 89, in decode
  248. z = self.post_quant_conv(z)
  249. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\venv\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
  250. return self._call_impl(*args, **kwargs)
  251. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\venv\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
  252. return forward_call(*args, **kwargs)
  253. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\extensions-builtin\Lora\networks.py", line 599, in network_Conv2d_forward
  254. return originals.Conv2d_forward(self, input)
  255. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\venv\lib\site-packages\torch\nn\modules\conv.py", line 460, in forward
  256. return self._conv_forward(input, self.weight, self.bias)
  257. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\venv\lib\site-packages\torch\nn\modules\conv.py", line 456, in _conv_forward
  258. return F.conv2d(input, weight, bias, self.stride,
  259. RuntimeError: Given groups=1, weight of size [4, 4, 1, 1], expected input[1, 8, 64, 64] to have 4 channels, but got 8 channels instead
  260. 🔄 Created fallback image: (512, 512)
  261. ✅ mid_freq band decoded: (512, 512)
  262. 🖼️ VAE decoding high_freq band...
  263. ⚠️ Error decoding latent to image: Given groups=1, weight of size [4, 4, 1, 1], expected input[1, 8, 64, 64] to have 4 channels, but got 8 channels instead
  264. Traceback (most recent call last):
  265. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\extensions\sd-webui-frequency-separation\scripts\frequency_separation.py", line 1303, in decode_latent_to_image
  266. decoded = p.sd_model.decode_first_stage(latent_for_decode)
  267. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\modules\sd_hijack_utils.py", line 22, in <lambda>
  268. setattr(resolved_obj, func_path[-1], lambda *args, **kwargs: self(*args, **kwargs))
  269. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\modules\sd_hijack_utils.py", line 36, in __call__
  270. return self.__orig_func(*args, **kwargs)
  271. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\venv\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
  272. return func(*args, **kwargs)
  273. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 826, in decode_first_stage
  274. return self.first_stage_model.decode(z)
  275. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\modules\lowvram.py", line 74, in first_stage_model_decode_wrap
  276. return first_stage_model_decode(z)
  277. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\repositories\stable-diffusion-stability-ai\ldm\models\autoencoder.py", line 89, in decode
  278. z = self.post_quant_conv(z)
  279. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\venv\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
  280. return self._call_impl(*args, **kwargs)
  281. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\venv\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
  282. return forward_call(*args, **kwargs)
  283. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\extensions-builtin\Lora\networks.py", line 599, in network_Conv2d_forward
  284. return originals.Conv2d_forward(self, input)
  285. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\venv\lib\site-packages\torch\nn\modules\conv.py", line 460, in forward
  286. return self._conv_forward(input, self.weight, self.bias)
  287. File "E:\A1111\StabilityMatrixData\Packages\Stable Diffusion WebUI Test RC\venv\lib\site-packages\torch\nn\modules\conv.py", line 456, in _conv_forward
  288. return F.conv2d(input, weight, bias, self.stride,
  289. RuntimeError: Given groups=1, weight of size [4, 4, 1, 1], expected input[1, 8, 64, 64] to have 4 channels, but got 8 channels instead
  290. 🔄 Created fallback image: (512, 512)
  291. ✅ high_freq band decoded: (512, 512)
  292. 🎨 Starting multi-VAE image space recombination using frequency_reconstruction...
  293. 📐 low_freq: (512, 512, 3) avg=0.0 std=0.0
  294. 📐 mid_freq: (512, 512, 3) avg=0.0 std=0.0
  295. 📐 high_freq: (512, 512, 3) avg=0.0 std=0.0
  296. 🌊 Using FREQUENCY RECONSTRUCTION with energy normalization...
  297. 🎵 Processing low_freq for frequency reconstruction...
  298. 📊 Using CORNER AVERAGE distance calculation (image space)
  299. 🎵 Processing mid_freq for frequency reconstruction...
  300. 📊 Using CORNER AVERAGE distance calculation (image space)
  301. 🎵 Processing high_freq for frequency reconstruction...
  302. 📊 Using CORNER AVERAGE distance calculation (image space)
  303. 💡 Final brightness (no energy correction): 0.0 (original: 0.0)
  304. 🎯 Final brightness: 0.0 (target: 0.0)
  305. 🎉 Multi-VAE recombination successful: (512, 512)
  306. 🎆 Image 1/1 frequency processing COMPLETE!
  307.  
  308. 🎉 ALL FREQUENCY SEPARATION WITH REAL DIFFUSION COMPLETE!
  309. ✨ Enhanced 1 images through frequency-domain processing
  310. 🎯 Each image processed through 3 separate diffusion runs
  311. ✅ Image 1 frequency enhancement complete!
  312. 🔄 Updated original tensor in-place on device: cpu
  313.  
  314. 🎉 Batch frequency enhancement complete! ADetailer will now process the enhanced images.
  315. Total progress: 60it [00:10, 5.51it/s]s]
  316. Ending job task(ibzf4lsl1rl3gtn) (12.14 seconds)
  317.  
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement
Public Pastes
Advertisement
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!