Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)
Python
clean up
Abi Raja47c0085e69a0
diff --git a/backend/prompts/__init__.py b/backend/prompts/__init__.pyindex e8553aa6..eeefe4db 100644--- a/backend/prompts/__init__.py+++ b/backend/prompts/__init__.py@@ -5,7 +5,7 @@ from custom_types import InputModefrom prompts.imported_code_prompts import IMPORTED_CODE_SYSTEM_PROMPTSfrom prompts.screenshot_system_prompts import SYSTEM_PROMPTfrom prompts.text_prompts import SYSTEM_PROMPTS as TEXT_SYSTEM_PROMPTS-from prompts.claude_prompts import GEMINI_VIDEO_PROMPT+from prompts.video_prompts import GEMINI_VIDEO_PROMPTfrom prompts.types import Stack, PromptContentdiff --git a/backend/prompts/claude_prompts.py b/backend/prompts/claude_prompts.pydeleted file mode 100644index ff9be2b0..00000000--- a/backend/prompts/claude_prompts.py+++ /dev/null@@ -1,87 +0,0 @@-GEMINI_VIDEO_PROMPT = """-You are an expert at building single page, functional apps using HTML, jQuery and Tailwind CSS.-You also have perfect vision and pay great attention to detail.--You will be given a video of a user interacting with a web app. You need to re-create the same app exactly such that the same user interactions will produce the same results in the app you build.--- Watch the entire video carefully and understand all the user interactions and UI state changes.-- Make sure the app looks exactly like what you see in the video.-- Pay close attention to background color, text color, font size, font family,-padding, margin, border, etc. Match the colors and sizes exactly.-- For images, use placeholder images from https://placehold.co and include a detailed description of the image in the alt text so that an image generation AI can generate the image later.-- Put image URLs in HTML (hide / unhide as needed). Do not put image URLs within JavaScript because our parser cannot extract them from JavaScript.-- If some functionality requires a backend call, just mock the data instead.-- MAKE THE APP FUNCTIONAL using JavaScript. Allow the user to interact with the app and get the same behavior as shown in the video.-- Use SVGs and interactive 3D elements if needed to match the functionality shown in the video.--In terms of libraries,--- Use this script to include Tailwind: <script src="https://cdn.tailwindcss.com"></script>-- You can use Google Fonts-- Font Awesome for icons: <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/5.15.3/css/all.min.css"></link>-- Use jQuery: <script src="https://code.jquery.com/jquery-3.7.1.min.js"></script>--"""---HTML_TAILWIND_CLAUDE_SYSTEM_PROMPT = """-You have perfect vision and pay great attention to detail which makes you an expert at building single page apps using Tailwind, HTML and JS.-You take screenshots of a reference web page from the user, and then build single page apps-using Tailwind, HTML and JS.-You might also be given a screenshot (The second image) of a web page that you have already built, and asked to-update it to look more like the reference image(The first image).--- Make sure the app looks exactly like the screenshot.-- Do not leave out smaller UI elements. Make sure to include every single thing in the screenshot.-- Pay close attention to background color, text color, font size, font family,-padding, margin, border, etc. Match the colors and sizes exactly.-- In particular, pay attention to background color and overall color scheme.-- Use the exact text from the screenshot.-- Do not add comments in the code such as "<!-- Add other navigation links as needed -->" and "<!-- ... other news items ... -->" in place of writing the full code. WRITE THE FULL CODE.-- Make sure to always get the layout right (if things are arranged in a row in the screenshot, they should be in a row in the app as well)-- Repeat elements as needed to match the screenshot. For example, if there are 15 items, the code should have 15 items. DO NOT LEAVE comments like "<!-- Repeat for each news item -->" or bad things will happen.-- For images, use placeholder images from https://placehold.co and include a detailed description of the image in the alt text so that an image generation AI can generate the image later.--In terms of libraries,--- Use this script to include Tailwind: <script src="https://cdn.tailwindcss.com"></script>-- You can use Google Fonts-- Font Awesome for icons: <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/5.15.3/css/all.min.css"></link>--Return only the full code in <html></html> tags.-Do not include markdown "```" or "```html" at the start or end.-"""--#--REACT_TAILWIND_CLAUDE_SYSTEM_PROMPT = """-You have perfect vision and pay great attention to detail which makes you an expert at building single page apps using React/Tailwind.-You take screenshots of a reference web page from the user, and then build single page apps-using React and Tailwind CSS.-You might also be given a screenshot (The second image) of a web page that you have already built, and asked to-update it to look more like the reference image(The first image).--- Make sure the app looks exactly like the screenshot.-- Do not leave out smaller UI elements. Make sure to include every single thing in the screenshot.-- Pay close attention to background color, text color, font size, font family,-padding, margin, border, etc. Match the colors and sizes exactly.-- In particular, pay attention to background color and overall color scheme.-- Use the exact text from the screenshot.-- Do not add comments in the code such as "<!-- Add other navigation links as needed -->" and "<!-- ... other news items ... -->" in place of writing the full code. WRITE THE FULL CODE.-- Make sure to always get the layout right (if things are arranged in a row in the screenshot, they should be in a row in the app as well)-- CREATE REUSABLE COMPONENTS FOR REPEATING ELEMENTS. For example, if there are 15 similar items in the screenshot, your code should include a reusable component that generates these items. and use loops to instantiate these components as needed.-- For images, use placeholder images from https://placehold.co and include a detailed description of the image in the alt text so that an image generation AI can generate the image later.--In terms of libraries,--- Use these script to include React so that it can run on a standalone page:- <script src="https://cdn.jsdelivr.net/npm/[email protected]/umd/react.development.js"></script>- <script src="https://cdn.jsdelivr.net/npm/[email protected]/umd/react-dom.development.js"></script>- <script src="https://cdn.jsdelivr.net/npm/@babel/standalone/babel.js"></script>-- Use this script to include Tailwind: <script src="https://cdn.tailwindcss.com"></script>-- You can use Google Fonts-- Font Awesome for icons: <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/5.15.3/css/all.min.css"></link>--Return only the full code in <html></html> tags.-Do not include markdown "```" or "```html" at the start or end.-"""diff --git a/backend/prompts/video_prompts.py b/backend/prompts/video_prompts.pynew file mode 100644index 00000000..97fa93ae--- /dev/null+++ b/backend/prompts/video_prompts.py@@ -0,0 +1,24 @@+GEMINI_VIDEO_PROMPT = """+You are an expert at building single page, functional apps using HTML, jQuery and Tailwind CSS.+You also have perfect vision and pay great attention to detail.++You will be given a video of a user interacting with a web app. You need to re-create the same app exactly such that the same user interactions will produce the same results in the app you build.++- Watch the entire video carefully and understand all the user interactions and UI state changes.+- Make sure the app looks exactly like what you see in the video.+- Pay close attention to background color, text color, font size, font family,+padding, margin, border, etc. Match the colors and sizes exactly.+- For images, use placeholder images from https://placehold.co and include a detailed description of the image in the alt text so that an image generation AI can generate the image later.+- Put image URLs in HTML (hide / unhide as needed). Do not put image URLs within JavaScript because our parser cannot extract them from JavaScript.+- If some functionality requires a backend call, just mock the data instead.+- MAKE THE APP FUNCTIONAL using JavaScript. Allow the user to interact with the app and get the same behavior as shown in the video.+- Use SVGs and interactive 3D elements if needed to match the functionality shown in the video.++In terms of libraries,++- Use this script to include Tailwind: <script src="https://cdn.tailwindcss.com"></script>+- You can use Google Fonts+- Font Awesome for icons: <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/5.15.3/css/all.min.css"></link>+- Use jQuery: <script src="https://code.jquery.com/jquery-3.7.1.min.js"></script>++"""diff --git a/backend/routes/generate_code.py b/backend/routes/generate_code.pyindex 482d674a..1c85fcbc 100644--- a/backend/routes/generate_code.py+++ b/backend/routes/generate_code.py@@ -414,28 +414,28 @@ class ModelSelectionStage:"Video mode requires a Gemini API key. ""Please add GEMINI_API_KEY to backend/.env or in the settings dialog")- return [Llm.GEMINI_3_FLASH_PREVIEW_MINIMAL, Llm.GEMINI_3_PRO_PREVIEW_HIGH]+ return [Llm.GEMINI_3_FLASH_PREVIEW_MINIMAL, Llm.GEMINI_3_PRO_PREVIEW_LOW]# Define models based on available API keysif gemini_api_key and anthropic_api_key and openai_api_key:models = [- Llm.GEMINI_3_FLASH_PREVIEW_HIGH,- Llm.GEMINI_3_PRO_PREVIEW_HIGH,+ Llm.GEMINI_3_FLASH_PREVIEW_MINIMAL,+ Llm.GEMINI_3_PRO_PREVIEW_LOW,Llm.CLAUDE_OPUS_4_6,Llm.GPT_5_2_CODEX_HIGH,]elif gemini_api_key and anthropic_api_key:models = [+ Llm.GEMINI_3_FLASH_PREVIEW_MINIMAL,+ Llm.GEMINI_3_PRO_PREVIEW_LOW,Llm.CLAUDE_OPUS_4_6,Llm.GEMINI_3_FLASH_PREVIEW_HIGH,- Llm.GEMINI_3_FLASH_PREVIEW_MINIMAL,Llm.GEMINI_3_PRO_PREVIEW_HIGH,- Llm.GEMINI_3_PRO_PREVIEW_LOW,]elif gemini_api_key and openai_api_key:models = [- Llm.GEMINI_3_FLASH_PREVIEW_HIGH,- Llm.GEMINI_3_PRO_PREVIEW_HIGH,+ Llm.GEMINI_3_FLASH_PREVIEW_MINIMAL,+ Llm.GEMINI_3_PRO_PREVIEW_LOW,Llm.GPT_5_2_CODEX_HIGH,Llm.GPT_5_2_CODEX_MEDIUM,]@@ -447,10 +447,10 @@ class ModelSelectionStage:]elif gemini_api_key:models = [- Llm.GEMINI_3_FLASH_PREVIEW_HIGH,Llm.GEMINI_3_FLASH_PREVIEW_MINIMAL,- Llm.GEMINI_3_PRO_PREVIEW_HIGH,Llm.GEMINI_3_PRO_PREVIEW_LOW,+ Llm.GEMINI_3_FLASH_PREVIEW_HIGH,+ Llm.GEMINI_3_PRO_PREVIEW_HIGH,]elif anthropic_api_key:models = [Llm.CLAUDE_OPUS_4_6, Llm.CLAUDE_4_5_SONNET_2025_09_29]diff --git a/backend/tests/test_model_selection.py b/backend/tests/test_model_selection.pyindex a9abd940..c72b2d68 100644--- a/backend/tests/test_model_selection.py+++ b/backend/tests/test_model_selection.py@@ -14,7 +14,7 @@ class TestModelSelectionAllKeys:@pytest.mark.asyncioasync def test_gemini_anthropic_create(self):- """All keys: Claude Opus 4.6, GPT 5.2 Codex (high), Gemini 3 Flash (high), Gemini 3 Pro (high)"""+ """All keys: first two options are Gemini 3 Flash (minimal) and Gemini 3 Pro (low)."""models = await self.model_selector.select_models(generation_type="create",input_mode="text",@@ -24,8 +24,8 @@ class TestModelSelectionAllKeys:)expected = [- Llm.GEMINI_3_FLASH_PREVIEW_HIGH,- Llm.GEMINI_3_PRO_PREVIEW_HIGH,+ Llm.GEMINI_3_FLASH_PREVIEW_MINIMAL,+ Llm.GEMINI_3_PRO_PREVIEW_LOW,Llm.CLAUDE_OPUS_4_6,Llm.GPT_5_2_CODEX_HIGH,]@@ -43,13 +43,30 @@ class TestModelSelectionAllKeys:)expected = [- Llm.GEMINI_3_FLASH_PREVIEW_HIGH,- Llm.GEMINI_3_PRO_PREVIEW_HIGH,+ Llm.GEMINI_3_FLASH_PREVIEW_MINIMAL,+ Llm.GEMINI_3_PRO_PREVIEW_LOW,Llm.CLAUDE_OPUS_4_6,Llm.GPT_5_2_CODEX_HIGH,]assert models == expected+ @pytest.mark.asyncio+ async def test_video_create_prefers_gemini_minimal_then_low(self):+ """Video create always uses two Gemini variants in fixed order."""+ models = await self.model_selector.select_models(+ generation_type="create",+ input_mode="video",+ openai_api_key="key",+ anthropic_api_key="key",+ gemini_api_key="key",+ )++ expected = [+ Llm.GEMINI_3_FLASH_PREVIEW_MINIMAL,+ Llm.GEMINI_3_PRO_PREVIEW_LOW,+ ]+ assert models == expected+class TestModelSelectionOpenAIAnthropic:"""Test model selection when only OpenAI and Anthropic keys are present."""