Instructions to use LyliaEngine/DynamicPose with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use LyliaEngine/DynamicPose with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("OnomaAIResearch/Illustrious-xl-early-release-v0", torch_dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("LyliaEngine/DynamicPose") prompt = "masterpiece,best quality,amazing quality,very aesthetic,absurdres,newest,,light particles, cinematic lighting,Visual impact,sharp focus, extreme aesthetic, BREAK 1woman, jumping off a helicopter, sniper rifle, holding a gun, scope, cityscape, flying, on the air " image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
| tags: | |
| - text-to-image | |
| - lora | |
| - diffusers | |
| - template:diffusion-lora | |
| widget: | |
| - output: | |
| url: images/01161-1989121474.png | |
| text: >- | |
| masterpiece,best quality,amazing quality,very | |
| aesthetic,absurdres,newest,,light particles, cinematic lighting,Visual | |
| impact,sharp focus, extreme aesthetic, BREAK 1woman, jumping off a | |
| helicopter, sniper rifle, holding a gun, scope, cityscape, flying, on the | |
| air | |
| parameters: | |
| negative_prompt: >- | |
| depth of field, blur, NSFW, deformed hand, bad hand, worst quality,low | |
| quality,logo,text,watermark,signature, bad quality,worst quality,worst | |
| detail,sketch,censor, simple background,transparent background, old, | |
| early, low quality, lowres, signature, username, logo, bad hands, mutated | |
| hands, mammal, anthro, | |
| - output: | |
| url: images/00692-2112480940.png | |
| text: >- | |
| masterpiece,best quality,amazing quality,very | |
| aesthetic,absurdres,newest,,light particles, cinematic lighting,Visual | |
| impact,sharp focus, extreme aesthetic, BREAK 1woman, pink hair, pink eyes, | |
| psychotic, yandere, maid outfit, holding a scythe, POV from below, on the | |
| floor, <lora:DynamicPoseIL2att_alpha1.0_rank4_noxattn_900steps:3>, | |
| <lora:TotalStyleEnhancer_alpha1.0_rank4_noxattn_100steps:1> | |
| parameters: | |
| negative_prompt: >- | |
| depth of field, blur, NSFW, deformed hand, bad hand, worst quality,low | |
| quality,logo,text,watermark,signature, bad quality,worst quality,worst | |
| detail,sketch,censor, simple background,transparent background, old, | |
| early, low quality, lowres, signature, username, logo, bad hands, mutated | |
| hands, mammal, anthro, | |
| - output: | |
| url: images/01026-3056547898.png | |
| text: >- | |
| masterpiece,best quality,amazing quality,very | |
| aesthetic,absurdres,newest,,light particles, cinematic lighting,Visual | |
| impact,sharp focus, extreme aesthetic, BREAK 1woman, jester aesthetic, | |
| chaotic energy, bells, multicolored outfit, mismatched stockings, harlequin | |
| pattern, mask half-off, wide grin, dramatic lighting, surreal background, | |
| floating cards, uncanny valley, twisted carnival, unsettling charm, tilted | |
| head, dynamic pose, tilted angle, spotlight, | |
| <lora:DynamicPoseIL2att_alpha1.0_rank4_noxattn_900steps:3.6> | |
| parameters: | |
| negative_prompt: >- | |
| depth of field, blur, NSFW, deformed hand, bad hand, worst quality,low | |
| quality,logo,text,watermark,signature, bad quality,worst quality,worst | |
| detail,sketch,censor, simple background,transparent background, old, | |
| early, low quality, lowres, signature, username, logo, bad hands, mutated | |
| hands, mammal, anthro, | |
| base_model: OnomaAIResearch/Illustrious-xl-early-release-v0 | |
| instance_prompt: dynamic pose, foreshortening, extreme perspective | |
| license: cdla-permissive-2.0 | |
| # DynamicPose | |
| <Gallery /> | |
| ## Model description | |
| A slider lora to help you make your poses more dynamic and in more extreme angles. | |
| Strength : 2.5 | |
| ## Trigger words | |
| You should use `dynamic pose` to trigger the image generation. | |
| You should use `foreshortening` to trigger the image generation. | |
| You should use `extreme perspective` to trigger the image generation. | |
| ## Source | |
| https://civitai.com/models/438059/dynamic-poses-slider-ponyxl?modelVersionId=1607510 | |
| ## Credit | |
| https://civitai.com/user/N4Talent | |
| ## Download model | |
| [Download](/LyliaEngine/DynamicPose/tree/main) them in the Files & versions tab. | |