tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
widget:
- text: Inference with 2 steps
output:
url: images/result_2steps.png
- text: Inference with 4 steps
output:
url: images/result_4steps.png
- text: Inference with 8 steps
output:
url: images/result_8steps.png
base_model: Lykon/dreamshaper-7
instance_prompt: tscd, hypersd
license: mit
TSCD-Dreamshaper-7
Model description
Fine-tune a distill LoRA version of Lykon/dreamshaper-7 using Time Segmented Consistency Model (TSCD) introduce in Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis
This LoRA is fine-tuned on laion/conceptual-captions-12m-webdataset for 16.000 iterations using unofficial training implementation at https://github.com/rootonchair/consistency_models_distill
Usage
```python import os import torch from diffusers import StableDiffusionPipeline, TCDScheduler
pipeline = StableDiffusionPipeline.from_pretrained("Lykon/dreamshaper-7", torch_dtype=torch.float16, safety_checker = None).to("cuda") pipeline.load_lora_weights("rootonchair/tscd-dreamshaper-7") pipeline.scheduler = TCDScheduler.from_config(pipeline.scheduler.config) test_prompts = [ "cgmech, white mecha robot, cape, science fiction, torn clothes, glowing, standing, robot joints, mecha, armor, cowboy shot, intense sunlight, silver dragonborn, outdoors, landscape, nature, volumetrics dtx", "Portrait photo of muscular bearded guy in a worn mech suit, elegant, sharp focus, photo by greg rutkowski, soft lighting, vibrant colors", "photo of a supercar, 8k uhd, high quality, road, sunset, motion blur, depth blur, cinematic, filmic image 4k", "a portrait of a white cat wearing glasses, highly detailed", "a beautiful runrise at the beach, cinematic, masterpiece", "A photo of beautiful mountain with realistic sunset and blue lake, highly detailed, masterpiece", "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k", "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" ] seed = 1234 images = pipeline(test_prompts, width=512, height=512, num_inference_steps=4, guidance_scale = 0, generator=torch.Generator(device='cuda').manual_seed(seed)).images ```
Trigger words
You should use tscd
to trigger the image generation.
You should use hypersd
to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.