Fooocus support
I tested SSD-1B.safetensors in Fooocus version 2.1.823, and it works as intended, with the speed and quality sampling settings.
The "extreme speed" setting does not work (Fooocus implementation of LCM), but it compensates that the generation speeds are much faster than those of standard SDXL models.
Image prompting works, variations and upscale also, outpainting/inpainting does not.
Outstanding model, keep up the good work.
Thanks for the feedback!
SSD-1B + LCM works fine with this my preset and consuming only 3.7Gb VRAM
{
"default_model": "SSD-1B-A1111.safetensors",
"default_refiner": "",
"default_refiner_switch": 0.5,
"default_loras": [["pytorch_lora_weights.safetensors",1.0],["None",1.0],["None",1.0],["None",1.0],["None",1.0]],
"default_advanced_checkbox": false,
"default_image_number": 1,
"default_cfg_scale": 1.0,
"default_sample_sharpness": 1.0,
"default_sampler": "dpmpp_2m_sde_gpu",
"default_scheduler": "karras",
"default_performance": "Extreme Speed",
"default_prompt": "redhead girl on sea shores",
"default_prompt_negative": "(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, double middle finger, (thumbless, six-fingered:1.2)",
"default_styles": ["Fooocus V2"],
"default_aspect_ratio": "1024*1024",
"checkpoint_downloads": {"SSD-1B-A1111.safetensors": "https://huggingface.co/segmind/SSD-1B/raw/main/SSD-1B-A1111.safetensors"},
"embeddings_downloads": {},
"lora_downloads": {"pytorch_lora_weights.safetensors": "https://huggingface.co/latent-consistency/lcm-lora-ssd-1b/resolve/main/pytorch_lora_weights.safetensors"}
}
That's Great!