Spaces:
Paused
Paused
Commit History
-
Fixes 500 error for some users
Verified signature8d11e37
-
Enhance image generation function by initializing random number generator for device-specific operations; update markdown instructions for clarity and improve HTML header formatting
55002dc -
Refactor load_tokenizer function to include error handling and device optimizations; streamline model loading process and improve memory management
eecb045 -
Enable bf16 in load_infinity function and enhance transform function with type hints and error handling; refactor joint_vi_vae_encode_decode for improved performance and error management
366fd1c -
Set CUDA launch blocking environment variable for improved debugging
27e1ebb -
Add CUDA availability check for input IDs and attention mask in prompt encoding
7434833 -
Refactor image generation process by removing gen_one_img function; streamline prompt encoding and inference steps
5c095cd -
Fix indentation in load_infinity function for better readability
e5b7e3e -
Remove unused image enhancement functions to streamline image processing
14626ab -
Enhance Gradio interface with detailed instructions and a custom HTML header for the Infinity Image Generator
aaa0ff6 -
Fixes
bc56be3 -
Refactor encode_prompt function by removing enable_positive_prompt parameter and related logic; streamline image generation process
715c7b0 -
Make the generator CPU
66cfd91 -
Refactoring
9d8246c -
Fix json issue
9508399 -
Refactoring
0e3e704 -
Initialize to CPU if no GPU
1776f2c -
Remove cache_enabled parameter from autocast context in load_infinity function for cleaner implementation
920cc4d -
Remove device initialization and logging from load_transformer function; set device parameter to None for flexibility
8e360af -
Make device optional in load_infinity function; set default to 'cuda' or 'cpu' based on availability and adjust autocast dtype handling
8e9da2c -
Enhance Infinity model loading by specifying device type in autocast context for improved performance
2d4f4be -
Optimize Infinity model loading by clearing CUDA cache and adjusting device assignment; remove redundant calls
9914b63 -
Add device and dtype logging in app.py for better debugging
54f9225 -
Refine prompt enhancement guidelines in app.py to focus on visual and sensory features; clarify output structure and examples
c493a61 -
Add prompt enhancement functionality and integrate Gradio client in app.py; update requirements.txt
836dd96 -
Update .gitignore to include weights folder and .pypirc
c0ec201 -
Refactor app.py to improve UI layout and rename weight download function; update import path for AutoEncoder in vae.py
f7f1ca1 -
Remove redundant text encoder model download and update tokenizer path in app.py
041b736 -
Refactor import statement for consistency in utils/misc.py
77e7720 -
Install flash-attn package with subprocess in app.py
1ce0fc2 -
Refactor import paths and update requirements to include timm
bd9b6e5 -
Add torchvision to requirements.txt
a251936 -
Remove unused dependencies from requirements.txt
9e62bbd -
Add initial project structure with requirements and utility functions
32287b3 -
initial commit
Verified signaturea8efd17