search

misobarisic / Diffusion-UI

Anything 4.5, Anything 3.0, Waifu Diffusion, Stable Diffusion 2.1, H Diffusion, Midjourney, Redshift
Apache License 2.0
63 stars 10 forks source link

The problem sometimes does not show photos #9

Closed tranthai2k2 closed 1 year ago

tranthai2k2 commented 1 year ago

Sorry if the wrong position i make pictures with lora it works great your model is great However, I don't know why your model is so good that it doesn't show the image even though in colab finished creating the image, but in the web, there is no image, hope you can help me https://colab.research.google.com/drive/1iwLtfEeoUTTVFZ08iVkvJ5jBhwKcspty?usp=sharing I just tweaked it to make it easier for me but the picture doesn't show up

misobarisic commented 1 year ago

The issue seems to be a temporary regression within gradio or the webui itself. Could you try changing the last line of run_webui to this !COMMANDLINE_ARGS="{other_args} {vae_args} {vram} --gradio-queue --gradio-auth {gradio_username}:{gradio_password}" REQS_FILE="requirements.txt" python launch.py

tranthai2k2 commented 1 year ago

image

misobarisic commented 1 year ago

This works for me

def run_webui():
  #@markdown Choose the vae you want
  vae = "Anime (Anything 4)" #@param ["Anime (Anything 3)", "Anime (Anything 4)", "Anime (Waifu Diffusion 1.4)", "Stable Diffusion", "None"]

  if vae == "Anime (Anything 3)":
    !wget -c https://huggingface.co/Linaqruf/anything-v3.0/resolve/main/Anything-V3.0.vae.pt -O {root_dir}/stable-diffusion-webui/models/Stable-diffusion/Anything-V3.0.vae.pt
    vae_args = "--vae-path " + root_dir + "/stable-diffusion-webui/models/Stable-diffusion/Anything-V3.0.vae.pt"
  if vae == "Anime (Anything 4)":
    !wget -c https://huggingface.co/andite/anything-v4.0/resolve/main/anything-v4.0.vae.pt -O {root_dir}/stable-diffusion-webui/models/Stable-diffusion/anything-v4.0.vae.pt
    vae_args = "--vae-path " + root_dir + "/stable-diffusion-webui/models/Stable-diffusion/anything-v4.0.vae.pt"
  if vae == "Anime (Waifu Diffusion 1.4)":
    !wget -c https://huggingface.co/hakurei/waifu-diffusion-v1-4/resolve/main/vae/kl-f8-anime.ckpt -O {root_dir}/stable-diffusion-webui/models/Stable-diffusion/kl-f8-anime.vae.pt
    vae_args = "--vae-path " + root_dir + "/stable-diffusion-webui/models/Stable-diffusion/kl-f8-anime.vae.pt"
  if vae == "Stable Diffusion":
    !wget https://huggingface.co/stabilityai/sd-vae-ft-mse-original/resolve/main/vae-ft-mse-840000-ema-pruned.ckpt -O {root_dir}/stable-diffusion-webui/models/Stable-diffusion/sd-v1-5.vae.pt
    vae_args = "--vae-path " + root_dir + "/stable-diffusion-webui/models/Stable-diffusion/sd-v1-5.vae.pt"

  %cd {root_dir}/stable-diffusion-webui/
  !COMMANDLINE_ARGS="{other_args} {vae_args} {vram} --gradio-queue --gradio-auth {gradio_username}:{gradio_password}" REQS_FILE="requirements.txt" python launch.py
tranthai2k2 commented 1 year ago

i think the problem is with !git clone https://github.com/acheong08/stable-diffusion-webui it's full but not stable and camenduru's it's stable but can't add autotag nor Lora and acheong08's it's unstable but it's both lora and autotag I'm sorry the code you edited and added is awesome it's stable and awesome if yes I'll recommend to my friends about your model it's awesome

misobarisic commented 1 year ago

Mine clones the latest commit from the A1111 webui repo 🤔

From what I can see, acheong08 has not pushed any commits of his own recently. He's been merging upstream changes

misobarisic commented 1 year ago

I have removed --gradio-queue since somebody else also reported an issue right after I pushed the fix.

image

tranthai2k2 commented 1 year ago

https://colab.research.google.com/drive/1iwLtfEeoUTTVFZ08iVkvJ5jBhwKcspty?usp=sharing#scrollTo=fAsaOpxoT-PC This model I tweaked to my liking, it's quite stable, but if possible, I still hope your model is updated to help stabilize the image export so it won't fail without image. Thank you for your model hope to have more models

tranthai2k2 commented 1 year ago

image image image image Even after creating an image, it still can't be retrieved, but the old image has been created

misobarisic commented 1 year ago

I am not experiencing such an issue. Hmm

Can you see the images in the gallery tab?

tranthai2k2 commented 1 year ago

my error times

misobarisic commented 1 year ago

A111#6898

misobarisic commented 1 year ago

I could reproduce the issue using your notebook and it was solved by adding --gradio-queue to launch args

misobarisic commented 1 year ago

I've pushed a new commit using gradio queue with tag complete extensions checkbox and lora as well. Test it out

tranthai2k2 commented 1 year ago

Error completing request Arguments: ('task(mwkjn3p8ul6fi5w)', 'masterpiece, best quality, twintails, wide sleeves, hands on hips, hand on hip, breasts, 1girl, dress, solo, clothing cutout, thighhighs, cleavage, chinese clothes, rating:safe, pelvic curtain, mole on breast, large breasts, mole on thigh , black hair, china dress, blush, smile, cleavage cutout, short hair, bare shoulders, blue sky, looking at viewer, covered navel, no panties, focused, upright, thigh-high, opposite, volumetric light, good light,, masterpiece, best quality, very detailed, wallpaper 8k cg unity extremely detailed, illustrations,((beautifully detailed) face) ), best quality, (((super detailed ))) , high quality, high resolution illustrations, high resolution , side light, ((best illustration)), high resolution, illustration, absurd, super detailed, intricate detail, perfect , highly detailed eyes ,yellow eyes, perfect light, (CG:1.2 color is extremely detailed),((bangs covering one eye))', 'nsfw, loli, small breasts, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts,signature, watermark, username, blurry, artist name, worst quality, low quality, (worst quality, low quality, extra digits, loli, loli face:1.3)', [], 32, 16, False, False, 2, 2, 7, 324660525.0, -1.0, 0, 0, 0, False, 648, 584, False, 0.7, 2, 'Latent', 0, 0, 0, 0, False, False, False, False, '', 1, '', 0, '', True, False, False) {} Traceback (most recent call last): File "/content/stable-diffusion-webui/modules/call_queue.py", line 56, in f res = list(func(*args, kwargs)) File "/content/stable-diffusion-webui/modules/call_queue.py", line 37, in f res = func(*args, *kwargs) File "/content/stable-diffusion-webui/modules/txt2img.py", line 52, in txt2img processed = process_images(p) File "/content/stable-diffusion-webui/modules/processing.py", line 476, in process_images res = process_images_inner(p) File "/content/stable-diffusion-webui/modules/processing.py", line 614, in process_images_inner samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, prompts=prompts) File "/content/stable-diffusion-webui/modules/processing.py", line 809, in sample samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x)) File "/content/stable-diffusion-webui/modules/sd_samplers.py", line 544, in sample samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={ File "/content/stable-diffusion-webui/modules/sd_samplers.py", line 447, in launch_sampling return func() File "/content/stable-diffusion-webui/modules/sd_samplers.py", line 544, in samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={ File "/usr/local/lib/python3.8/dist-packages/torch/autograd/grad_mode.py", line 27, in decorate_context return func(args, kwargs) File "/content/stable-diffusion-webui/repositories/k-diffusion/k_diffusion/sampling.py", line 553, in sample_dpmpp_sde denoised = model(x, sigmas[i] * s_in, extra_args) File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1190, in _call_impl return forward_call(*input, *kwargs) File "/content/stable-diffusion-webui/modules/sd_samplers.py", line 350, in forward x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond={"c_crossattn": [tensor[a:b]], "c_concat": [image_cond_in[a:b]]}) File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1190, in _call_impl return forward_call(input, kwargs) File "/content/stable-diffusion-webui/repositories/k-diffusion/k_diffusion/external.py", line 112, in forward eps = self.get_eps(input * c_in, self.sigma_to_t(sigma), kwargs) File "/content/stable-diffusion-webui/repositories/k-diffusion/k_diffusion/external.py", line 138, in get_eps return self.inner_model.apply_model(args, kwargs) File "/content/stable-diffusion-webui/repositories/stable-diffusion-stability-ai/ldm/models/diffusion/ddpm.py", line 858, in apply_model x_recon = self.model(x_noisy, t, cond) File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1190, in _call_impl return forward_call(input, kwargs) File "/content/stable-diffusion-webui/repositories/stable-diffusion-stability-ai/ldm/models/diffusion/ddpm.py", line 1329, in forward out = self.diffusion_model(x, t, context=cc) File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1190, in _call_impl return forward_call(*input, kwargs) File "/content/stable-diffusion-webui/repositories/stable-diffusion-stability-ai/ldm/modules/diffusionmodules/openaimodel.py", line 776, in forward h = module(h, emb, context) File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1190, in _call_impl return forward_call(*input, *kwargs) File "/content/stable-diffusion-webui/repositories/stable-diffusion-stability-ai/ldm/modules/diffusionmodules/openaimodel.py", line 84, in forward x = layer(x, context) File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1190, in _call_impl return forward_call(input, kwargs) File "/content/stable-diffusion-webui/repositories/stable-diffusion-stability-ai/ldm/modules/attention.py", line 324, in forward x = block(x, context=context[i]) File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1190, in _call_impl return forward_call(*input, *kwargs) File "/content/stable-diffusion-webui/repositories/stable-diffusion-stability-ai/ldm/modules/attention.py", line 259, in forward return checkpoint(self._forward, (x, context), self.parameters(), self.checkpoint) File "/content/stable-diffusion-webui/repositories/stable-diffusion-stability-ai/ldm/modules/diffusionmodules/util.py", line 114, in checkpoint return CheckpointFunction.apply(func, len(inputs), args) File "/content/stable-diffusion-webui/repositories/stable-diffusion-stability-ai/ldm/modules/diffusionmodules/util.py", line 129, in forward output_tensors = ctx.run_function(ctx.input_tensors) File "/content/stable-diffusion-webui/repositories/stable-diffusion-stability-ai/ldm/modules/attention.py", line 262, in _forward x = self.attn1(self.norm1(x), context=context if self.disable_self_attn else None) + x File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1190, in _call_impl return forward_call(input, **kwargs) File "/content/stable-diffusion-webui/modules/sd_hijack_optimizations.py", line 309, in xformers_attention_forward out = xformers.ops.memory_efficient_attention(q, k, v, attn_bias=None, op=get_xformers_flash_attention_op(q, k, v)) File "/usr/local/lib/python3.8/dist-packages/xformers/ops/fmha/init.py", line 203, in memory_efficient_attention return _memory_efficient_attention( File "/usr/local/lib/python3.8/dist-packages/xformers/ops/fmha/init.py", line 299, in _memory_efficient_attention return _memory_efficient_attention_forward( File "/usr/local/lib/python3.8/dist-packages/xformers/ops/fmha/init.py", line 315, in _memory_efficient_attention_forward op = _dispatch_fw(inp) File "/usr/local/lib/python3.8/dist-packages/xformers/ops/fmha/dispatch.py", line 95, in _dispatch_fw return _run_priority_list( File "/usr/local/lib/python3.8/dist-packages/xformers/ops/fmha/dispatch.py", line 70, in _run_priority_list raise NotImplementedError(msg) image hey bro it's not even better

misobarisic commented 1 year ago

The UI at least starts, doesn't throw an error because --gradio-queue is present. This is an issue with xformers then. I noticed your initial version of the notebook you sent used xformers 0.0.15 whereas mine was updated to 0.0.16 recently. Might be worth trying to use the previous version then.

!pip install https://github.com/camenduru/stable-diffusion-webui-colab/releases/download/0.0.16/xformers-0.0.16+814314d.d20230118-cp38-cp38-linux_x86_64.whl --> !pip install https://github.com/camenduru/stable-diffusion-webui-colab/releases/download/0.0.15/xformers-0.0.15+e163309.d20230103-cp38-cp38-linux_x86_64.whl

Or you could just disable xformers since I cannot guarantee it will work.

tranthai2k2 commented 1 year ago

I don't know why after I press run in drive it works very smoothly and has a very good image but I haven't pressed it before but it doesn't show the image If possible, you can adjust it to save only images, don't run in drive, it saves all the files to the drive, so it's a bit heavy it stays the same unless run in drive image

misobarisic commented 1 year ago

The issue is still out of my control. Though I will add an option for just saving images to gdrive nonetheless.