Instructions to use HyHorX/AlphaGen-v1-preview-max with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use HyHorX/AlphaGen-v1-preview-max with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("HyHorX/AlphaGen-v1-preview-max", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
| { | |
| "recreate_based_on_previous_image": true, | |
| "max_height_width": 1280, | |
| "aspect_ratio": "1:1", | |
| "max_recreate_time": 6, | |
| "dynamic_threshold": 0.93, | |
| "max_char": 400, | |
| "max_prompt_len": 400, | |
| "steps_per_generate": 50, | |
| "guidance_scale": 8.0, | |
| "seed": -1, | |
| "scheduler": "dpm++", | |
| "clip_skip": 1, | |
| "enable_xformers": true, | |
| "enable_attention_slicing": true, | |
| "enable_vae_slicing": true, | |
| "precision": "fp16", | |
| "batch_size": 1, | |
| "num_images_per_prompt": 1, | |
| "prompt_enhance": true, | |
| "prompt_style": "ultra detailed, masterpiece, best quality, cinematic lighting, volumetric light, sharp focus, 8k, highly realistic", | |
| "rl_mode": "qwen3_strict", | |
| "score_source": "qwen3_vl", | |
| "score_format": "strict_float", | |
| "fallback_score_min": 0.80, | |
| "use_multi_aspect_score": true, | |
| "score_weights": { | |
| "prompt_alignment": 0.4, | |
| "visual_quality": 0.3, | |
| "detail_level": 0.2, | |
| "realism": 0.1 | |
| }, | |
| "2_check_process": true, | |
| "diffusers_pipeline": "StableDiffusion3Pipeline", | |
| "output_dir": "outputs", | |
| "auto_save": true, | |
| "file_format": "png" | |
| } |