AcademiaSD/sd-forge-fluxtools-v2

Fork 0

mirror of https://github.com/AcademiaSD/sd-forge-fluxtools-v2.git synced 2026-11-04 23:27:24 +00:00

[GH-ISSUE #4] Incorrect depth mask. I upload a 1024x1536 image and get a 512x512 depth mask. #4

New issue

Open

opened 2026-10-30 21:03:56 +00:00 by bsakaguchi · 5 comments

bsakaguchi commented

2026-10-30 21:03:56 +00:00

Owner

Originally created by @sashaok123 on GitHub (Apr 14, 2025).
Original GitHub issue: https://github.com/AcademiaSD/sd-forge-fluxtools-v2/issues/4

Incorrect depth mask. I upload a 1024x1536 image and get a 512x512 depth mask.

And when trying to generate, an error occurs: RuntimeError: at 1 andmat2 shapes cannot be multiplied (6144x128 and 64x3072)

[Unload] Trying to free 1966.08 MB for cuda:0 with 1 models keep loaded ... Current free memory is 6077.13 MB ... Done.
  0%|                                                                                           | 0/30 [00:00<?, ?it/s]
Traceback (most recent call last):
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules_forge\main_thread.py", line 30, in work
    self.result = self.func(*self.args, **self.kwargs)
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules\txt2img.py", line 131, in txt2img_function
    processed = processing.process_images(p)
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules\processing.py", line 842, in process_images
    res = process_images_inner(p)
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules\processing.py", line 990, in process_images_inner
    samples_ddim = p.sample(conditioning=p.c, unconditional_conditioning=p.uc, seeds=p.seeds, subseeds=p.subseeds, subseed_strength=p.subseed_strength, prompts=p.prompts)
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules\processing.py", line 1387, in sample
    samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules\sd_samplers_kdiffusion.py", line 238, in sample
    samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules\sd_samplers_common.py", line 278, in launch_sampling
    return func()
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules\sd_samplers_kdiffusion.py", line 238, in <lambda>
    samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\k_diffusion\sampling.py", line 779, in sample_ipndm
    denoised = model(x_cur, t_cur * s_in, **extra_args)
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\venv\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\venv\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl
    return forward_call(*args, **kwargs)
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules\sd_samplers_cfg_denoiser.py", line 199, in forward
    denoised, cond_pred, uncond_pred = sampling_function(self, denoiser_params=denoiser_params, cond_scale=cond_scale, cond_composition=cond_composition)
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\backend\sampling\sampling_function.py", line 362, in sampling_function
    denoised, cond_pred, uncond_pred = sampling_function_inner(model, x, timestep, uncond, cond, cond_scale, model_options, seed, return_full=True)
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\backend\sampling\sampling_function.py", line 303, in sampling_function_inner
    cond_pred, uncond_pred = calc_cond_uncond_batch(model, cond, uncond_, x, timestep, model_options)
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\backend\sampling\sampling_function.py", line 273, in calc_cond_uncond_batch
    output = model.apply_model(input_x, timestep_, **c).chunk(batch_chunks)
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\backend\modules\k_model.py", line 45, in apply_model
    model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, **extra_conds).float()
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\venv\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\venv\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl
    return forward_call(*args, **kwargs)
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\backend\nn\flux.py", line 418, in forward
    out = self.inner_forward(img, img_ids, context, txt_ids, timestep, y, guidance)
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\backend\nn\flux.py", line 375, in inner_forward
    img = self.img_in(img)
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\venv\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\venv\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl
    return forward_call(*args, **kwargs)
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\backend\operations.py", line 147, in forward
    return torch.nn.functional.linear(x, weight, bias)
RuntimeError: mat1 and mat2 shapes cannot be multiplied (6144x128 and 64x3072)
mat1 and mat2 shapes cannot be multiplied (6144x128 and 64x3072)

Originally created by @sashaok123 on GitHub (Apr 14, 2025). Original GitHub issue: https://github.com/AcademiaSD/sd-forge-fluxtools-v2/issues/4 Incorrect depth mask. I upload a 1024x1536 image and get a 512x512 depth mask. ![Image](https://github.com/user-attachments/assets/db4e5bbc-00bb-4141-86d5-465e5502cf99) And when trying to generate, an error occurs: RuntimeError: at 1 andmat2 shapes cannot be multiplied (6144x128 and 64x3072) ![Image](https://github.com/user-attachments/assets/82e9200d-fc08-42e5-a9b9-feedba0d79ae) ``` [Unload] Trying to free 1966.08 MB for cuda:0 with 1 models keep loaded ... Current free memory is 6077.13 MB ... Done. 0%| | 0/30 [00:00<?, ?it/s] Traceback (most recent call last): File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules_forge\main_thread.py", line 30, in work self.result = self.func(*self.args, **self.kwargs) File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules\txt2img.py", line 131, in txt2img_function processed = processing.process_images(p) File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules\processing.py", line 842, in process_images res = process_images_inner(p) File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules\processing.py", line 990, in process_images_inner samples_ddim = p.sample(conditioning=p.c, unconditional_conditioning=p.uc, seeds=p.seeds, subseeds=p.subseeds, subseed_strength=p.subseed_strength, prompts=p.prompts) File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules\processing.py", line 1387, in sample samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x)) File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules\sd_samplers_kdiffusion.py", line 238, in sample samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs)) File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules\sd_samplers_common.py", line 278, in launch_sampling return func() File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules\sd_samplers_kdiffusion.py", line 238, in <lambda> samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs)) File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\k_diffusion\sampling.py", line 779, in sample_ipndm denoised = model(x_cur, t_cur * s_in, **extra_args) File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\venv\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\venv\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl return forward_call(*args, **kwargs) File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules\sd_samplers_cfg_denoiser.py", line 199, in forward denoised, cond_pred, uncond_pred = sampling_function(self, denoiser_params=denoiser_params, cond_scale=cond_scale, cond_composition=cond_composition) File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\backend\sampling\sampling_function.py", line 362, in sampling_function denoised, cond_pred, uncond_pred = sampling_function_inner(model, x, timestep, uncond, cond, cond_scale, model_options, seed, return_full=True) File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\backend\sampling\sampling_function.py", line 303, in sampling_function_inner cond_pred, uncond_pred = calc_cond_uncond_batch(model, cond, uncond_, x, timestep, model_options) File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\backend\sampling\sampling_function.py", line 273, in calc_cond_uncond_batch output = model.apply_model(input_x, timestep_, **c).chunk(batch_chunks) File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\backend\modules\k_model.py", line 45, in apply_model model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, **extra_conds).float() File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\venv\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\venv\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl return forward_call(*args, **kwargs) File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\backend\nn\flux.py", line 418, in forward out = self.inner_forward(img, img_ids, context, txt_ids, timestep, y, guidance) File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\backend\nn\flux.py", line 375, in inner_forward img = self.img_in(img) File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\venv\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\venv\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl return forward_call(*args, **kwargs) File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\backend\operations.py", line 147, in forward return torch.nn.functional.linear(x, weight, bias) RuntimeError: mat1 and mat2 shapes cannot be multiplied (6144x128 and 64x3072) mat1 and mat2 shapes cannot be multiplied (6144x128 and 64x3072) ```

bsakaguchi commented

2026-10-30 21:03:57 +00:00

Author

Owner

@Rolf-100R commented on GitHub (Apr 15, 2025):

RuntimeError: mat1 and mat2 shapes cannot be multiplied (6144x128 and 64x3072)
mat1 and mat2 shapes cannot be multiplied (6144x128 and 64x3072)

I had the same problem https://github.com/AcademiaSD/sd-forge-fluxtools-v2/issues/3

Turns out I didn't have

ae.safetensors
clip_l.safetensors
t5xxl_fp8_e4m3fn.safetensors

As soon as I downloaded them and put them in, everything worked. But the image quality is terrible. It feels like the lora's are not working.

@Rolf-100R commented on GitHub (Apr 15, 2025): > RuntimeError: mat1 and mat2 shapes cannot be multiplied (6144x128 and 64x3072) mat1 and mat2 shapes cannot be multiplied (6144x128 and 64x3072) I had the same problem https://github.com/AcademiaSD/sd-forge-fluxtools-v2/issues/3 Turns out I didn't have ae.safetensors clip_l.safetensors t5xxl_fp8_e4m3fn.safetensors As soon as I downloaded them and put them in, everything worked. But the image quality is terrible. It feels like the lora's are not working.

bsakaguchi commented

2026-10-30 21:03:57 +00:00

Author

Owner

@sashaok123 commented on GitHub (Apr 15, 2025):

It feels like the lora's are not working.

LoRA support doesn't seem to be announced.

@sashaok123 commented on GitHub (Apr 15, 2025): > It feels like the lora's are not working. LoRA support doesn't seem to be announced.

bsakaguchi commented

2026-10-30 21:03:58 +00:00

Author

Owner

@AcademiaSD commented on GitHub (Apr 18, 2025):

Incorrect depth mask. I upload a 1024x1536 image and get a 512x512 depth mask.

And when trying to generate, an error occurs: RuntimeError: at 1 andmat2 shapes cannot be multiplied (6144x128 and 64x3072)

[Unload] Trying to free 1966.08 MB for cuda:0 with 1 models keep loaded ... Current free memory is 6077.13 MB ... Done.
  0%|                                                                                           | 0/30 [00:00<?, ?it/s]
Traceback (most recent call last):
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules_forge\main_thread.py", line 30, in work
    self.result = self.func(*self.args, **self.kwargs)
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules\txt2img.py", line 131, in txt2img_function
    processed = processing.process_images(p)
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules\processing.py", line 842, in process_images
    res = process_images_inner(p)
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules\processing.py", line 990, in process_images_inner
    samples_ddim = p.sample(conditioning=p.c, unconditional_conditioning=p.uc, seeds=p.seeds, subseeds=p.subseeds, subseed_strength=p.subseed_strength, prompts=p.prompts)
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules\processing.py", line 1387, in sample
    samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules\sd_samplers_kdiffusion.py", line 238, in sample
    samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules\sd_samplers_common.py", line 278, in launch_sampling
    return func()
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules\sd_samplers_kdiffusion.py", line 238, in <lambda>
    samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\k_diffusion\sampling.py", line 779, in sample_ipndm
    denoised = model(x_cur, t_cur * s_in, **extra_args)
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\venv\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\venv\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl
    return forward_call(*args, **kwargs)
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules\sd_samplers_cfg_denoiser.py", line 199, in forward
    denoised, cond_pred, uncond_pred = sampling_function(self, denoiser_params=denoiser_params, cond_scale=cond_scale, cond_composition=cond_composition)
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\backend\sampling\sampling_function.py", line 362, in sampling_function
    denoised, cond_pred, uncond_pred = sampling_function_inner(model, x, timestep, uncond, cond, cond_scale, model_options, seed, return_full=True)
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\backend\sampling\sampling_function.py", line 303, in sampling_function_inner
    cond_pred, uncond_pred = calc_cond_uncond_batch(model, cond, uncond_, x, timestep, model_options)
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\backend\sampling\sampling_function.py", line 273, in calc_cond_uncond_batch
    output = model.apply_model(input_x, timestep_, **c).chunk(batch_chunks)
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\backend\modules\k_model.py", line 45, in apply_model
    model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, **extra_conds).float()
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\venv\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\venv\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl
    return forward_call(*args, **kwargs)
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\backend\nn\flux.py", line 418, in forward
    out = self.inner_forward(img, img_ids, context, txt_ids, timestep, y, guidance)
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\backend\nn\flux.py", line 375, in inner_forward
    img = self.img_in(img)
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\venv\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\venv\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl
    return forward_call(*args, **kwargs)
  File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\backend\operations.py", line 147, in forward
    return torch.nn.functional.linear(x, weight, bias)
RuntimeError: mat1 and mat2 shapes cannot be multiplied (6144x128 and 64x3072)
mat1 and mat2 shapes cannot be multiplied (6144x128 and 64x3072)

The error mat1 and mat2 shapes cannot be multiplied (6144x128 and 64x3072) appears when the appropriate checkpoint is not selected, in this case the depth checkpoint, the preprocessor always generates square depth maps of 512x512, but they are adapted to be usable.

@AcademiaSD commented on GitHub (Apr 18, 2025): > Incorrect depth mask. I upload a 1024x1536 image and get a 512x512 depth mask. > > ![Image](https://github.com/user-attachments/assets/db4e5bbc-00bb-4141-86d5-465e5502cf99) > > And when trying to generate, an error occurs: RuntimeError: at 1 andmat2 shapes cannot be multiplied (6144x128 and 64x3072) > > ![Image](https://github.com/user-attachments/assets/82e9200d-fc08-42e5-a9b9-feedba0d79ae) > > ``` > [Unload] Trying to free 1966.08 MB for cuda:0 with 1 models keep loaded ... Current free memory is 6077.13 MB ... Done. > 0%| | 0/30 [00:00<?, ?it/s] > Traceback (most recent call last): > File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules_forge\main_thread.py", line 30, in work > self.result = self.func(*self.args, **self.kwargs) > File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules\txt2img.py", line 131, in txt2img_function > processed = processing.process_images(p) > File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules\processing.py", line 842, in process_images > res = process_images_inner(p) > File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules\processing.py", line 990, in process_images_inner > samples_ddim = p.sample(conditioning=p.c, unconditional_conditioning=p.uc, seeds=p.seeds, subseeds=p.subseeds, subseed_strength=p.subseed_strength, prompts=p.prompts) > File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules\processing.py", line 1387, in sample > samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x)) > File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules\sd_samplers_kdiffusion.py", line 238, in sample > samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs)) > File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules\sd_samplers_common.py", line 278, in launch_sampling > return func() > File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules\sd_samplers_kdiffusion.py", line 238, in <lambda> > samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs)) > File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\k_diffusion\sampling.py", line 779, in sample_ipndm > denoised = model(x_cur, t_cur * s_in, **extra_args) > File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\venv\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl > return self._call_impl(*args, **kwargs) > File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\venv\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl > return forward_call(*args, **kwargs) > File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\modules\sd_samplers_cfg_denoiser.py", line 199, in forward > denoised, cond_pred, uncond_pred = sampling_function(self, denoiser_params=denoiser_params, cond_scale=cond_scale, cond_composition=cond_composition) > File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\backend\sampling\sampling_function.py", line 362, in sampling_function > denoised, cond_pred, uncond_pred = sampling_function_inner(model, x, timestep, uncond, cond, cond_scale, model_options, seed, return_full=True) > File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\backend\sampling\sampling_function.py", line 303, in sampling_function_inner > cond_pred, uncond_pred = calc_cond_uncond_batch(model, cond, uncond_, x, timestep, model_options) > File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\backend\sampling\sampling_function.py", line 273, in calc_cond_uncond_batch > output = model.apply_model(input_x, timestep_, **c).chunk(batch_chunks) > File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\backend\modules\k_model.py", line 45, in apply_model > model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, **extra_conds).float() > File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\venv\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl > return self._call_impl(*args, **kwargs) > File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\venv\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl > return forward_call(*args, **kwargs) > File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\backend\nn\flux.py", line 418, in forward > out = self.inner_forward(img, img_ids, context, txt_ids, timestep, y, guidance) > File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\backend\nn\flux.py", line 375, in inner_forward > img = self.img_in(img) > File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\venv\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl > return self._call_impl(*args, **kwargs) > File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\venv\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl > return forward_call(*args, **kwargs) > File "C:\!NeuralNetwork\!stable-diffusion-webui-forge\backend\operations.py", line 147, in forward > return torch.nn.functional.linear(x, weight, bias) > RuntimeError: mat1 and mat2 shapes cannot be multiplied (6144x128 and 64x3072) > mat1 and mat2 shapes cannot be multiplied (6144x128 and 64x3072) > ``` The error mat1 and mat2 shapes cannot be multiplied (6144x128 and 64x3072) appears when the appropriate checkpoint is not selected, in this case the depth checkpoint, the preprocessor always generates square depth maps of 512x512, but they are adapted to be usable.

bsakaguchi commented

2026-10-30 21:03:58 +00:00

Author

Owner

@sashaok123 commented on GitHub (Apr 19, 2025):

checkpoint is not selected

Do you ONLY support the original checkpoint?
But what about checkpoints that work great in Forge, which already include VAE and text encoders? For example: https://civitai.com/models/637170/
Or NF4 checkpoints versions 1 and 2. And also GGUF?

@sashaok123 commented on GitHub (Apr 19, 2025): > checkpoint is not selected Do you ONLY support the original checkpoint? But what about checkpoints that work great in Forge, which already include VAE and text encoders? For example: https://civitai.com/models/637170/ Or NF4 checkpoints versions 1 and 2. And also GGUF?

bsakaguchi commented

2026-10-30 21:03:58 +00:00

Author

Owner

@AcademiaSD commented on GitHub (Apr 20, 2025):

checkpoint is not selected

Do you ONLY support the original checkpoint? But what about checkpoints that work great in Forge, which already include VAE and text encoders? For example: https://civitai.com/models/637170/ Or NF4 checkpoints versions 1 and 2. And also GGUF?

The extension supports checkpoints that work in Forge, nf4, gguf, etc., but keep in mind that you need canny, depth or fill checkpoints, except for redux mode, where you can use general Flux checkpoints.

@AcademiaSD commented on GitHub (Apr 20, 2025): > > checkpoint is not selected > > Do you ONLY support the original checkpoint? But what about checkpoints that work great in Forge, which already include VAE and text encoders? For example: https://civitai.com/models/637170/ Or NF4 checkpoints versions 1 and 2. And also GGUF? The extension supports checkpoints that work in Forge, nf4, gguf, etc., but keep in mind that you need canny, depth or fill checkpoints, except for redux mode, where you can use general Flux checkpoints.

No labels

No milestone

No project

No assignees

1 participant

Notifications

Due date

The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference

AcademiaSD/sd-forge-fluxtools-v2#4

No description provided.

Rows
Columns