Skip to content

New image generation model and LLMs#7

Merged
MathObsession merged 1 commit into
mainfrom
NewModels_imageGen
Jun 21, 2026
Merged

New image generation model and LLMs#7
MathObsession merged 1 commit into
mainfrom
NewModels_imageGen

Conversation

@MathObsession

Copy link
Copy Markdown
Owner

No description provided.

@MathObsession MathObsession requested a review from Copilot June 21, 2026 06:05
@MathObsession MathObsession merged commit 55358a6 into main Jun 21, 2026
1 check passed
@MathObsession MathObsession deleted the NewModels_imageGen branch June 21, 2026 06:06

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Adds new versioned assistant scripts (V1.7.1 and V1.8) and documentation, with V1.8 extending the voice-first loop to include Stable Diffusion image generation and terminal previews.

Changes:

  • Introduces V1.8 assistant loop with image-generation detection and Stable Diffusion generation.
  • Adds V1.8 documentation covering features, requirements, and usage.
  • Adds V1.7.1 snapshot (script + README) alongside existing versions.

Reviewed changes

Copilot reviewed 5 out of 5 changed files in this pull request and generated 14 comments.

Show a summary per file
File Description
V1.8/main.py New V1.8 assistant implementation including image-generation flow and terminal preview integration.
V1.8/README.md New V1.8 documentation describing features, setup, and limitations.
V1.8/test2.py Small helper script intended to preview a generated image with chafa.
V1.7.1/main.py New V1.7.1 assistant implementation snapshot (pre-image-generation).
V1.7.1/README.md New V1.7.1 documentation describing setup and usage.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Comment thread V1.8/test2.py
Comment thread V1.8/main.py
Comment thread V1.8/main.py
from rich.console import Console
from rich.text import Text
from diffusers import StableDiffusionPipeline
from term_image.image import from_file
Comment thread V1.8/main.py
Comment on lines +24 to +26
console = Console()
terminal_width = os.get_terminal_size().columns
columns, _ = shutil.get_terminal_size()
Comment thread V1.8/main.py
Comment on lines +128 to +137
prompt = image_generation_filter.message.content
image = pipe(prompt, num_inference_steps=20).images[0]
image.save("generated_image.png")
small_width = 60
subprocess.run([
"chafa",
"/Users/lakshyaprajapati/Documents/Repositories/generated_image.png",
"--symbols", "block",
f"--size={small_width}"
])
Comment thread V1.7.1/README.md
Comment on lines +80 to +82
## License

This project does not include a license. Add one if needed.
Comment thread V1.7.1/main.py
Comment on lines +167 to +175
voice_recogniser = sr.Recognizer()
with sr.Microphone() as source1:
r.adjust_for_ambient_noise(source1, duration=0.2)
prompt_text = "*Do you want to continue the conversation? Yes or No?*"
console.print(Text.from_ansi(format_for_terminal(prompt_text)))
speak("Do you want to continue the conversation? Yes or No?")
time.sleep(0.01)
console.print(Text.from_ansi(format_for_terminal("*Listening for your response...*")))
audio1 = voice_recogniser.listen(source1)
Comment thread V1.7.1/main.py
Comment on lines +182 to +186
except sr.UnknownValueError:
console.print(Text.from_ansi(format_for_terminal("Could not understand audio")))
print()

norm = re.sub(r'[^\w]', '', voice_continue_recogniser).lower()
Comment thread V1.7.1/main.py
Comment on lines +82 to +89
app = os.popen(
f'mdfind \'kMDItemKind == "Application"\' | grep -i "{target}" | head -n 1'
).read().strip()
if app:
os.system(f'open "{app}"')
else:
os.system(f'open "https://{target.replace(" ", "")}.com"')
is_app_open += 1
Comment thread V1.8/main.py
Comment on lines +89 to +96
app = os.popen(
f'mdfind \'kMDItemKind == "Application"\' | grep -i "{target}" | head -n 1'
).read().strip()
if app:
os.system(f'open "{app}"')
else:
os.system(f'open "https://{target.replace(" ", "")}.com"')
is_app_open += 1
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants