search

comfyanonymous / ComfyUI

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
https://www.comfy.org/
GNU General Public License v3.0
57.77k stars 6.13k forks source link

Empty Latent Image Node Settings #589

Closed kyle215ps3 closed 1 year ago

kyle215ps3 commented 1 year ago

Nevermind, I figured out how to make custom sizes with the convert the width to height into inputs and then use integer node to put in the sizes.

kyle215ps3 commented 1 year ago

nevermind again, looks like putting in 592 as the height causes an issue. But doesn't at 512 for example. Is there another way to use the height of 592? Seems like the empty latent image node doesn't accept certain inputs like 600 or 592 and so on. Update: So I was able to edit the efficiency node to change the step count on image size and get to the resolution I want but I still get the same error.

I have two errors the first is before using efficiency nodes and the second is from after using and editing the step count. Not sure if it's the exact same error.

Error before the update on using efficiency node:

Traceback (most recent call last): File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 195, in execute recursive_execute(self.server, prompt, self.outputs, x, extra_data, executed) File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 58, in recursive_execute recursive_execute(server, prompt, outputs, input_unique_id, extra_data, executed) File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 58, in recursive_execute recursive_execute(server, prompt, outputs, input_unique_id, extra_data, executed) File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 67, in recursive_execute outputs[unique_id] = getattr(obj, obj.FUNCTION)(input_data_all) File "D:\ComfyUI_windows_portable\ComfyUI\nodes.py", line 816, in sample return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise) File "D:\ComfyUI_windows_portable\ComfyUI\nodes.py", line 787, in common_ksampler samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, File "D:\ComfyUI_windows_portable\ComfyUI\comfy\sample.py", line 79, in sample samples = sampler.sample(noise, positive_copy, negative_copy, cfg=cfg, latent_image=latent_image, start_step=start_step, last_step=last_step, force_full_denoise=force_full_denoise, denoise_mask=noise_mask, sigmas=sigmas, callback=callback) File "D:\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 666, in sample samples = getattr(k_diffusionsampling, "sample{}".format(self.sampler))(self.model_k, noise, sigmas, extra_args=extra_args, callback=k_callback) File "D:\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context return func(*args, *kwargs) File "D:\ComfyUI_windows_portable\ComfyUI\comfy\k_diffusion\sampling.py", line 594, in sample_dpmpp_2m denoised = model(x, sigmas[i] s_in, extra_args) File "D:\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(*args, kwargs) File "D:\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 283, in forward out = self.inner_model(x, sigma, cond=cond, uncond=uncond, cond_scale=cond_scale, cond_concat=cond_concat, model_options=model_options) File "D:\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(*args, *kwargs) File "D:\ComfyUI_windows_portable\ComfyUI\comfy\k_diffusion\external.py", line 114, in forward eps = self.get_eps(input c_in, self.sigma_to_t(sigma), kwargs) File "D:\ComfyUI_windows_portable\ComfyUI\comfy\k_diffusion\external.py", line 140, in get_eps return self.inner_model.apply_model(args, kwargs) File "D:\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 271, in apply_model out = sampling_function(self.inner_model.apply_model, x, timestep, uncond, cond, cond_scale, cond_concat, model_options=model_options) File "D:\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 250, in sampling_function cond, uncond = calc_cond_uncond_batch(model_function, cond, uncond, x, timestep, max_total_area, cond_concat, model_options) File "D:\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 227, in calc_cond_uncond_batch output = model_function(inputx, timestep, cond=c).chunk(batch_chunks) File "D:\ComfyUI_windows_portable\ComfyUI\comfy\ldm\models\diffusion\ddpm.py", line 859, in apply_model x_recon = self.model(x_noisy, t, cond) File "D:\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(args, *kwargs) File "D:\ComfyUI_windows_portable\ComfyUI\comfy\ldm\models\diffusion\ddpm.py", line 1337, in forward out = self.diffusion_model(x, t, context=cc, control=control, transformer_options=transformer_options) File "D:\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(args, **kwargs) File "D:\ComfyUI_windows_portable\ComfyUI\comfy\ldm\modules\diffusionmodules\openaimodel.py", line 816, in forward h = th.cat([h, hsp], dim=1) RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 20 but got size 19 for tensor number 1 in the list.

Error 2 Traceback (most recent call last): File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 195, in execute recursive_execute(self.server, prompt, self.outputs, x, extra_data, executed) File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 67, in recursive_execute outputs[unique_id] = getattr(obj, obj.FUNCTION)(input_data_all) File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\efficiency-nodes-comfyui\efficiency_nodes.py", line 290, in sample samples = common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, File "D:\ComfyUI_windows_portable\ComfyUI\nodes.py", line 787, in common_ksampler samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, File "D:\ComfyUI_windows_portable\ComfyUI\comfy\sample.py", line 79, in sample samples = sampler.sample(noise, positive_copy, negative_copy, cfg=cfg, latent_image=latent_image, start_step=start_step, last_step=last_step, force_full_denoise=force_full_denoise, denoise_mask=noise_mask, sigmas=sigmas, callback=callback) File "D:\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 666, in sample samples = getattr(k_diffusionsampling, "sample{}".format(self.sampler))(self.model_k, noise, sigmas, extra_args=extra_args, callback=k_callback) File "D:\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context return func(*args, *kwargs) File "D:\ComfyUI_windows_portable\ComfyUI\comfy\k_diffusion\sampling.py", line 594, in sample_dpmpp_2m denoised = model(x, sigmas[i] s_in, extra_args) File "D:\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(*args, kwargs) File "D:\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 283, in forward out = self.inner_model(x, sigma, cond=cond, uncond=uncond, cond_scale=cond_scale, cond_concat=cond_concat, model_options=model_options) File "D:\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(*args, *kwargs) File "D:\ComfyUI_windows_portable\ComfyUI\comfy\k_diffusion\external.py", line 114, in forward eps = self.get_eps(input c_in, self.sigma_to_t(sigma), kwargs) File "D:\ComfyUI_windows_portable\ComfyUI\comfy\k_diffusion\external.py", line 140, in get_eps return self.inner_model.apply_model(args, kwargs) File "D:\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 271, in apply_model out = sampling_function(self.inner_model.apply_model, x, timestep, uncond, cond, cond_scale, cond_concat, model_options=model_options) File "D:\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 250, in sampling_function cond, uncond = calc_cond_uncond_batch(model_function, cond, uncond, x, timestep, max_total_area, cond_concat, model_options) File "D:\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 227, in calc_cond_uncond_batch output = model_function(inputx, timestep, cond=c).chunk(batch_chunks) File "D:\ComfyUI_windows_portable\ComfyUI\comfy\ldm\models\diffusion\ddpm.py", line 859, in apply_model x_recon = self.model(x_noisy, t, cond) File "D:\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(args, *kwargs) File "D:\ComfyUI_windows_portable\ComfyUI\comfy\ldm\models\diffusion\ddpm.py", line 1337, in forward out = self.diffusion_model(x, t, context=cc, control=control, transformer_options=transformer_options) File "D:\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(args, **kwargs) File "D:\ComfyUI_windows_portable\ComfyUI\comfy\ldm\modules\diffusionmodules\openaimodel.py", line 816, in forward h = th.cat([h, hsp], dim=1) RuntimeError:

BlenderNeko commented 1 year ago

The denoiser in ComfyUI currently only supports resolutions that are increments of 64, If you need something that is not an increment of 64, your options are resizing or padding/cropping

kyle215ps3 commented 1 year ago

The denoiser in ComfyUI currently only supports resolutions that are increments of 64, If you need something that is not an increment of 64, your options are resizing or padding/cropping

damnn xD I hope they can allow a way to change it, I want to recreate some images on comfy UI I made from A1111 haha.

kyle215ps3 commented 1 year ago

The denoiser in ComfyUI currently only supports resolutions that are increments of 64, If you need something that is not an increment of 64, your options are resizing or padding/cropping

just found out the latent image resolution got updated and i can now get the resolution i need. Thank you if you had anything to do with it!! :D Much appreciated!!