HOME | DD

Description
Funny enough this slime pouring is the complete opposite of the last example, seemingly getting the pour right realistically. Shrug? And that is not a pixie haircut, well I guess she is sitting. nor is that a dutch angle shot. So thinking the LoRA is more overbaked than on thought, and probably on too few images, so will need to really ramp up the data set for next LoRA.

I wish the prompt showed all the dynamic prompts I use. Here is I believe the example prompt, followed by the random selection and what was ended up with, I don't think I went dynamic emotions till the following set, as you can see it adds some of the prompts and struggles with others:

SPDOH, photo of a young woman, {short|very short|medium|long} {black|blonde|red|auburn|brown|light brown} hair, green slime (substance) pouring down on head, {standing|kneeling|sitting} in {bathtub|shower|park|classroom|office|bedroom|backyard|gameshow studio|salon|barbershop}, wearing {1-2$$black|blue|brown|green|grey|purple|pink|white|violet|yellow|orange} {bikini|dress|pants and shirt|suit|t-shirt and jeans|t-shirt and skirt|t-shrit and shorts|bathing suit|miniskirt and crop top|blouse and pants|blouse and skirt|lingerie|schoolgirl outfit|schoolgirl costume|maid costume|underwear| underwear and bra|pajamas}, smiling, happy, rim lighting, studio lighting, dslr, ultra quality, sharp focus, tack sharp, dof, film grain, Fujifilm XT3, crystal clear, 8k UHD, award winning,

parameters
SPDOH, dutch angle photo of a young woman, very short pixe cut black hair, sideswept bangs, green slime (substance) pouring down on head, sitting in office, wearing pink,purple t-shirt and skirt, smiling, happy, rim lighting, studio lighting, dslr, ultra quality, sharp focus, tack sharp, dof, film grain, Fujifilm XT3, crystal clear, 8k UHD, award winning,
Negative prompt: disfigured, ugly, bad, immature, cartoon, anime, 3d, painting, b&w, hat, veil, water, out of frame
Steps: 150, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 2893528167, Size: 768x1280, Model hash: 0f1b80cfe8, Model: dreamshaperXL10_alpha2Xl10, VAE hash: 63aeecb90f, VAE: sdxl_vae.safetensors, Denoising strength: 0.1, Hires upscale: 2, Hires steps: 10, Hires upscaler: 4x_NMKD-Superscale-SP_178000_G, Lora hashes: "SPDOH-000020: 0a733c13270b", Version: v1.6.0

Description
Funny enough this slime pouring is the complete opposite of the last example, seemingly getting the pour right realistically. Shrug? And that is not a pixie haircut, well I guess she is sitting. nor is that a dutch angle shot. So thinking the LoRA is more overbaked than on thought, and probably on too few images, so will need to really ramp up the data set for next LoRA.

I wish the prompt showed all the dynamic prompts I use. Here is I believe the example prompt, followed by the random selection and what was ended up with, I don't think I went dynamic emotions till the following set, as you can see it adds some of the prompts and struggles with others:

SPDOH, photo of a young woman, {short|very short|medium|long} {black|blonde|red|auburn|brown|light brown} hair, green slime (substance) pouring down on head, {standing|kneeling|sitting} in {bathtub|shower|park|classroom|office|bedroom|backyard|gameshow studio|salon|barbershop}, wearing {1-2$$black|blue|brown|green|grey|purple|pink|white|violet|yellow|orange} {bikini|dress|pants and shirt|suit|t-shirt and jeans|t-shirt and skirt|t-shrit and shorts|bathing suit|miniskirt and crop top|blouse and pants|blouse and skirt|lingerie|schoolgirl outfit|schoolgirl costume|maid costume|underwear| underwear and bra|pajamas}, smiling, happy, rim lighting, studio lighting, dslr, ultra quality, sharp focus, tack sharp, dof, film grain, Fujifilm XT3, crystal clear, 8k UHD, award winning,

parameters
SPDOH, dutch angle photo of a young woman, very short pixe cut black hair, sideswept bangs, green slime (substance) pouring down on head, sitting in office, wearing pink,purple t-shirt and skirt, smiling, happy, rim lighting, studio lighting, dslr, ultra quality, sharp focus, tack sharp, dof, film grain, Fujifilm XT3, crystal clear, 8k UHD, award winning,
Negative prompt: disfigured, ugly, bad, immature, cartoon, anime, 3d, painting, b&w, hat, veil, water, out of frame
Steps: 150, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 2893528167, Size: 768x1280, Model hash: 0f1b80cfe8, Model: dreamshaperXL10_alpha2Xl10, VAE hash: 63aeecb90f, VAE: sdxl_vae.safetensors, Denoising strength: 0.1, Hires upscale: 2, Hires steps: 10, Hires upscaler: 4x_NMKD-Superscale-SP_178000_G, Lora hashes: "SPDOH-000020: 0a733c13270b", Version: v1.6.0