|
|
--- |
|
|
title: UltraPixel Multi-Stage (Community Fixed) |
|
|
emoji: π¨ |
|
|
colorFrom: blue |
|
|
colorTo: purple |
|
|
sdk: gradio |
|
|
sdk_version: 5.49.1 |
|
|
app_file: app.py |
|
|
pinned: false |
|
|
license: apache-2.0 |
|
|
--- |
|
|
|
|
|
# π¨ UltraPixel Multi-Stage Generator (Community Fixed) |
|
|
|
|
|
A **properly working** UltraPixel-style high-resolution image generator that actually respects your parameter inputs. |
|
|
|
|
|
## What's Different From Original UltraPixel Spaces? |
|
|
|
|
|
The original public UltraPixel spaces have a critical flaw - they **hardcode CFG and timesteps inside the generation function**, making the UI sliders meaningless: |
|
|
|
|
|
```python |
|
|
# Original broken code: |
|
|
extras.sampling_configs['cfg'] = 4 # β Always uses 4! |
|
|
extras.sampling_configs['timesteps'] = 20 # β Ignores your slider! |
|
|
``` |
|
|
|
|
|
### This Space Fixes That β
|
|
|
|
|
|
- **Real CFG Control**: Your slider values are actually passed to the model |
|
|
- **Real Steps Control**: Set your own timesteps (10-100) per stage |
|
|
- **Memory Optimized**: Won't OOM on ZeroGPU (max 3072Γ3072 with tiling) |
|
|
- **No Login Required**: Public access for easy testing |
|
|
|
|
|
## Features |
|
|
|
|
|
- π― **3-Stage Pipeline**: Stable Cascade architecture (Stage C β B β A) |
|
|
- π§ **Independent Controls**: Separate CFG/steps for each stage |
|
|
- πΎ **Memory Safe**: Aggressive cleanup between stages, forced tiling |
|
|
- β±οΈ **120s Per Stage**: Each stage gets fresh GPU allocation |
|
|
- π **Public Access**: No authentication needed |
|
|
|
|
|
## How to Use |
|
|
|
|
|
### Standard Workflow (3-4 minutes total) |
|
|
|
|
|
1. **Stage C - Generate Initial Latent** (~30-60s) |
|
|
- Enter your prompt |
|
|
- Set CFG (recommended: 7.5) and Steps (recommended: 30) |
|
|
- Click "Generate Stage C" |
|
|
- Wait for completion |
|
|
|
|
|
2. **Wait for GPU availability** (if needed during high traffic) |
|
|
|
|
|
3. **Stage B - Upscale Latent** (~30-50s) |
|
|
- Adjust CFG (recommended: 5.0) and Steps (recommended: 15) |
|
|
- Click "Generate Stage B" |
|
|
- Uses the latent from Stage C automatically |
|
|
|
|
|
4. **Wait again if needed** |
|
|
|
|
|
5. **Stage A - Final Decode** (~60-90s) |
|
|
- Keep "Use Tiling" checked (prevents OOM) |
|
|
- Click "Generate Final Image" |
|
|
- Download your high-res result! |
|
|
|
|
|
### Optimal Settings π‘ |
|
|
|
|
|
- **Stage C**: CFG 7-8, Steps 30-40 |
|
|
- **Stage B**: CFG 4-6, Steps 15-20 |
|
|
- **Stage A**: Always use tiling |
|
|
- **Resolution Limits**: Max 3072Γ3072 for stability (1536Γ1536 per stage C/B) |
|
|
- **For Training Data**: Generate at 3072px, then downscale to 1024px for optimal quality |
|
|
|
|
|
## Technical Details |
|
|
|
|
|
### Memory Management |
|
|
|
|
|
Each stage runs in isolated `@spaces.GPU(duration=120)` calls: |
|
|
- Models loaded only when needed |
|
|
- Aggressive `torch.cuda.empty_cache()` after each stage |
|
|
- Latents stored in-memory (automatically cleaned after 1 hour) |
|
|
- VAE tiling enabled for Stage A decode |
|
|
|
|
|
### Resolution Scaling |
|
|
|
|
|
- **Stage C Input**: 512-1536px (base resolution) |
|
|
- **Stage B Output**: 2Γ Stage C (1024-3072px) |
|
|
- **Stage A Output**: Full decode to target resolution |
|
|
- **Memory Usage**: ~20-30GB peak per stage (safe for ZeroGPU) |
|
|
|
|
|
## Why This Matters |
|
|
|
|
|
Many public AI spaces claim to offer "full control" but secretly override your parameters. This leads to: |
|
|
- β Inconsistent results despite changing settings |
|
|
- β Users wasting time tweaking sliders that do nothing |
|
|
- β Frustration when trying to reproduce outputs |
|
|
|
|
|
This space guarantees that **your inputs = actual model parameters**. |
|
|
|
|
|
## Deployment Notes |
|
|
|
|
|
Built specifically for: |
|
|
- ZeroGPU compatibility (120s duration per stage) |
|
|
- Public/unlogged access |
|
|
- High-resolution output (up to 3072Γ3072 stable) |
|
|
- Proper parameter control |
|
|
|
|
|
## Credits |
|
|
|
|
|
- **Stable Cascade**: Stability AI |
|
|
- **Original UltraPixel Concept**: Various community implementations |
|
|
- **This Implementation**: Community-fixed version with proper parameter control |
|
|
|
|
|
## License |
|
|
|
|
|
Apache 2.0 |
|
|
|