Describe the bug
Through alternative prompts, I'm trying to add blank prompts to allow prompts being skipped randomlyMisunderstood the feature yet this is a bug.
However [| or || or |] would fail generate.
Considered a bug because using a space like [ | seems fixing the problem yet I'm not sure if this works as desired. Alternative Prompts is nevertheless a lottery thing and needs some large batch to test.
To Reproduce
Steps to reproduce the behavior:
Enter "[|" or "||" or "|]" in prompt.
Click on 'Generate.'
See error, outputs attached
Expected behavior
A blank prompt would be randomly chosen.
I assume the [from::when] prompt is [from:to black prompt:when] so this should be similar?
Desktop (please complete the following information):
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "C:\STDF\stable-diffusion-webui\venv\lib\site-packages\lark\visitors.py", line 116, in _call_userfunc
return f(children)
File "C:\STDF\stable-diffusion-webui\modules\prompt_parser.py", line 82, in start
return ''.join(flatten(args))
File "C:\STDF\stable-diffusion-webui\modules\prompt_parser.py", line 81, in flatten
yield from flatten(gen)
File "C:\STDF\stable-diffusion-webui\modules\prompt_parser.py", line 80, in flatten
for gen in x:
File "C:\STDF\stable-diffusion-webui\modules\prompt_parser.py", line 87, in default
yield from child
RuntimeError: generator raised StopIteration
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "C:\STDF\stable-diffusion-webui\modules\ui.py", line 212, in f
res = list(func(*args, *kwargs))
File "C:\STDF\stable-diffusion-webui\webui.py", line 64, in f
res = func(args, **kwargs)
File "C:\STDF\stable-diffusion-webui\modules\txt2img.py", line 44, in txt2img
processed = process_images(p)
File "C:\STDF\stable-diffusion-webui\modules\processing.py", line 393, in process_images
c = prompt_parser.get_multicond_learned_conditioning(shared.sd_model, prompts, p.steps)
File "C:\STDF\stable-diffusion-webui\modules\prompt_parser.py", line 203, in get_multicond_learned_conditioning
learned_conditioning = get_learned_conditioning(model, prompt_flat_list, steps)
File "C:\STDF\stable-diffusion-webui\modules\prompt_parser.py", line 127, in get_learned_conditioning
prompt_schedules = get_learned_conditioning_prompt_schedules(prompts, steps)
File "C:\STDF\stable-diffusion-webui\modules\prompt_parser.py", line 100, in get_learned_conditioning_prompt_schedules
promptdict = {prompt: get_schedule(prompt) for prompt in set(prompts)}
File "C:\STDF\stable-diffusion-webui\modules\prompt_parser.py", line 100, in
promptdict = {prompt: get_schedule(prompt) for prompt in set(prompts)}
File "C:\STDF\stable-diffusion-webui\modules\prompt_parser.py", line 98, in get_schedule
return [[t, at_step(t, tree)] for t in collect_steps(steps, tree)]
File "C:\STDF\stable-diffusion-webui\modules\prompt_parser.py", line 98, in
return [[t, at_step(t, tree)] for t in collect_steps(steps, tree)]
File "C:\STDF\stable-diffusion-webui\modules\prompt_parser.py", line 88, in at_step
return AtStep().transform(tree)
File "C:\STDF\stable-diffusion-webui\venv\lib\site-packages\lark\visitors.py", line 153, in transform
return self._transform_tree(tree)
File "C:\STDF\stable-diffusion-webui\venv\lib\site-packages\lark\visitors.py", line 149, in _transform_tree
return self._call_userfunc(tree, children)
File "C:\STDF\stable-diffusion-webui\venv\lib\site-packages\lark\visitors.py", line 120, in _call_userfunc
raise VisitError(tree.data, tree, e)
lark.exceptions.VisitError: Error trying to process rule "start":
Describe the bug Through alternative prompts, I'm trying to add blank prompts
to allow prompts being skipped randomlyMisunderstood the feature yet this is a bug. However [| or || or |] would fail generate. Considered a bug because using a space like [ | seems fixing the problem yet I'm not sure if this works as desired. Alternative Prompts is nevertheless a lottery thing and needs some large batch to test. To Reproduce Steps to reproduce the behavior:Expected behavior A blank prompt would be randomly chosen. I assume the
[from::when]
prompt is[from:to black prompt:when]
so this should be similar?Desktop (please complete the following information):
The above exception was the direct cause of the following exception:
Traceback (most recent call last): File "C:\STDF\stable-diffusion-webui\venv\lib\site-packages\lark\visitors.py", line 116, in _call_userfunc return f(children) File "C:\STDF\stable-diffusion-webui\modules\prompt_parser.py", line 82, in start return ''.join(flatten(args)) File "C:\STDF\stable-diffusion-webui\modules\prompt_parser.py", line 81, in flatten yield from flatten(gen) File "C:\STDF\stable-diffusion-webui\modules\prompt_parser.py", line 80, in flatten for gen in x: File "C:\STDF\stable-diffusion-webui\modules\prompt_parser.py", line 87, in default yield from child RuntimeError: generator raised StopIteration
During handling of the above exception, another exception occurred:
Traceback (most recent call last): File "C:\STDF\stable-diffusion-webui\modules\ui.py", line 212, in f res = list(func(*args, *kwargs)) File "C:\STDF\stable-diffusion-webui\webui.py", line 64, in f res = func(args, **kwargs) File "C:\STDF\stable-diffusion-webui\modules\txt2img.py", line 44, in txt2img processed = process_images(p) File "C:\STDF\stable-diffusion-webui\modules\processing.py", line 393, in process_images c = prompt_parser.get_multicond_learned_conditioning(shared.sd_model, prompts, p.steps) File "C:\STDF\stable-diffusion-webui\modules\prompt_parser.py", line 203, in get_multicond_learned_conditioning learned_conditioning = get_learned_conditioning(model, prompt_flat_list, steps) File "C:\STDF\stable-diffusion-webui\modules\prompt_parser.py", line 127, in get_learned_conditioning prompt_schedules = get_learned_conditioning_prompt_schedules(prompts, steps) File "C:\STDF\stable-diffusion-webui\modules\prompt_parser.py", line 100, in get_learned_conditioning_prompt_schedules promptdict = {prompt: get_schedule(prompt) for prompt in set(prompts)} File "C:\STDF\stable-diffusion-webui\modules\prompt_parser.py", line 100, in
promptdict = {prompt: get_schedule(prompt) for prompt in set(prompts)}
File "C:\STDF\stable-diffusion-webui\modules\prompt_parser.py", line 98, in get_schedule
return [[t, at_step(t, tree)] for t in collect_steps(steps, tree)]
File "C:\STDF\stable-diffusion-webui\modules\prompt_parser.py", line 98, in
return [[t, at_step(t, tree)] for t in collect_steps(steps, tree)]
File "C:\STDF\stable-diffusion-webui\modules\prompt_parser.py", line 88, in at_step
return AtStep().transform(tree)
File "C:\STDF\stable-diffusion-webui\venv\lib\site-packages\lark\visitors.py", line 153, in transform
return self._transform_tree(tree)
File "C:\STDF\stable-diffusion-webui\venv\lib\site-packages\lark\visitors.py", line 149, in _transform_tree
return self._call_userfunc(tree, children)
File "C:\STDF\stable-diffusion-webui\venv\lib\site-packages\lark\visitors.py", line 120, in _call_userfunc
raise VisitError(tree.data, tree, e)
lark.exceptions.VisitError: Error trying to process rule "start":
generator raised StopIteration `