Comments (8)
Thank you @dfjunk and @SlappedWithSilence for providing additional information.
I was able to confirm that the issue was indeed caused by hires fix and batch_count
> 1, not batch_size
. It seems hires fix logic may have changed in the latest WebUI update.
At any rate, I believe I have fixed it internally - a new version of Unprompted will be made available in the coming days.
from unprompted.
Hi all,
This issue has been resolved in the newly released Unprompted v10.2.0.
from unprompted.
Additionally, this is the output in unprompted 9.15
*** Error running process_batch: X:\STABLEDIFFUSION\AUTOMATIC11111\extensions_unprompted\scripts\unprompted.py
Traceback (most recent call last):
File "X:\STABLEDIFFUSION\AUTOMATIC11111\extensions_unprompted\scripts\unprompted.py", line 737, in process_batch
if "extra_network_data" in p: extra_networks.deactivate(p, p.extra_network_data)
TypeError: argument of type 'StableDiffusionProcessingTxt2Img' is not iterable
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "X:\STABLEDIFFUSION\AUTOMATIC11111\modules\scripts.py", line 643, in process_batch
script.process_batch(p, *script_args, **kwargs)
File "X:\STABLEDIFFUSION\AUTOMATIC11111\extensions\_unprompted\scripts\unprompted.py", line 739, in process_batch
self.log.exception("Exception while deactiating extra networks")
AttributeError: 'Scripts' object has no attribute 'log'
Error is different but images are generated
from unprompted.
Hi @Dawgmastah,
Thank you for reaching out. In Unprompted v10.1.0, I am able to generate images with a batch_size
of 2 and hires fix enabled.
Looking at your console output, it appears that the problem may be related to ControlNet. Have you tried without ControlNet enabled?
from unprompted.
Hi @Dawgmastah,
Thank you for reaching out. In Unprompted v10.1.0, I am able to generate images with a
batch_size
of 2 and hires fix enabled.Looking at your console output, it appears that the problem may be related to ControlNet. Have you tried without ControlNet enabled?
Since they never responded, I figured I'd chip in here. I wonder if it's possible they meant "Batch count". I get "IndexError: index 1 is out of bounds for dimension 0 with size 1" whenever I try a batch count more than 1 when using hires.fix, and I don't use controlnet. I made sure adetailer was off too since I usually use that. It runs the first one fine, and then the second one runs fine right up until it switches to the hires.fix process. Hope this helps. Also sorry if the format below is wrong, I'm not very familiar with github.
Traceback (most recent call last):
File "H:\stable-diffusion\stable-diffusion-webui\modules\call_queue.py", line 57, in f
res = list(func(*args, **kwargs))
^^^^^^^^^^^^^^^^^^^^^
File "H:\stable-diffusion\stable-diffusion-webui\modules\call_queue.py", line 36, in f
res = func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "H:\stable-diffusion\stable-diffusion-webui\modules\txt2img.py", line 55, in txt2img
processed = processing.process_images(p)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "H:\stable-diffusion\stable-diffusion-webui\modules\processing.py", line 732, in process_images
res = process_images_inner(p)
^^^^^^^^^^^^^^^^^^^^^^^
File "H:\stable-diffusion\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\batch_hijack.py", line 42, in processing_process_images_hijack
return getattr(processing, '__controlnet_original_process_images_inner')(p, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "H:\stable-diffusion\stable-diffusion-webui\modules\processing.py", line 867, 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 "H:\stable-diffusion\stable-diffusion-webui\modules\processing.py", line 1156, in sample
return self.sample_hr_pass(samples, decoded_samples, seeds, subseeds, subseed_strength, prompts)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "H:\stable-diffusion\stable-diffusion-webui\modules\processing.py", line 1242, in sample_hr_pass
samples = self.sampler.sample_img2img(self, samples, noise, self.hr_c, self.hr_uc, steps=self.hr_second_pass_steps or self.steps, image_conditioning=image_conditioning)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "H:\stable-diffusion\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 188, in sample_img2img
samples = self.launch_sampling(t_enc + 1, lambda: self.func(self.model_wrap_cfg, xi, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "H:\stable-diffusion\stable-diffusion-webui\modules\sd_samplers_common.py", line 261, in launch_sampling
return func()
^^^^^^
File "H:\stable-diffusion\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 188, in
samples = self.launch_sampling(t_enc + 1, lambda: self.func(self.model_wrap_cfg, xi, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "H:\stable-diffusion\stable-diffusion-webui\venv\Lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "H:\stable-diffusion\stable-diffusion-webui\repositories\k-diffusion\k_diffusion\sampling.py", line 594, in sample_dpmpp_2m
denoised = model(x, sigmas[i] * s_in, **extra_args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "H:\stable-diffusion\stable-diffusion-webui\venv\Lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "H:\stable-diffusion\stable-diffusion-webui\modules\sd_samplers_cfg_denoiser.py", line 125, in forward
x_in = torch.cat([torch.stack([x[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [x])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "H:\stable-diffusion\stable-diffusion-webui\modules\sd_samplers_cfg_denoiser.py", line 125, in
x_in = torch.cat([torch.stack([x[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [x])
^^^^^^^^^^^^^^^^^^^^^^^^
File "H:\stable-diffusion\stable-diffusion-webui\modules\sd_samplers_cfg_denoiser.py", line 125, in
x_in = torch.cat([torch.stack([x[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [x])
~^^^
IndexError: index 1 is out of bounds for dimension 0 with size 1
from unprompted.
This issue occurs for me as well.
i7 8700k,
RTX 2080 (Gaming Driver)
32GB RAM
Up to on sdwebui and unprompted.
from unprompted.
Hi all,
This issue has been resolved in the newly released Unprompted v10.2.0.
Thank you so much, it works great! I've been using this extension non-stop since I found it, and this fix makes it even better for my workflow. Just wanted to say a quick thank you again for all of this.
from unprompted.
That's awesome to hear, @dfjunk. Thank you for the kind words!
from unprompted.
Related Issues (20)
- Seed errors when Batch Count > 1 HOT 1
- img2img_autosize shortscript broken with 1.6 HOT 4
- [set width] and [set height] are not applied correctly when batch count > 1 HOT 3
- Batch size has weird effects on temp images generated by zoom_enhance HOT 1
- zoom_enhance with controlnet crashes, python stack strace HOT 1
- Encoding problem with icons HOT 1
- 'NoneType' object does not support item assignment HOT 8
- zoom_enhance with bypass_adaptive_hires bug HOT 4
- txt2mask with fastsam, clip_surgery HOT 1
- Broken interaction between prompt, hires fix and batch count HOT 5
- Unprompted cannot differentiate between a template file and a template subfolder when named the same HOT 3
- Unprompted has stopped being deterministic HOT 9
- show the controlnet image after generation HOT 3
- ImageIO does not generally support reading folders. HOT 1
- (ERROR) Failed to install opencv-python dependency for Unprompted - [faceswap] insightface functions may not work HOT 2
- unable to write .json files _all_external and _external flags HOT 1
- processor_res vars won't work with sdxl controlnets HOT 4
- txt2mask with batch only applying to first image with "inpaint not masked"
- Bodysnatcher + Adetailer: Pillow fails when inverting txt2mask: OSError: not supported for this image mode HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from unprompted.