Image Generation Playground

🐣 NewBie Image Exp0.1

A 3.5B parameter experimental DiT model built on Next-DiT and Lumina insights

Prompt

<character_1>
<n>original_character</n>
<gender>1girl</gender>
<appearance>blonde_hair, long_hair</appearance>
<clothing>large_hat, white_hat, white_blouse, puffy_sleeves, shoulder cutout, black_skirt, shirt_tucked_in, socks, shoes</clothing>
<expression>smile, confident</expression>
<action>sitting, reclining, arm support, from above, female focus, close-up, dutch angle, solo</action>
<position>center, looking_up</position>
</character_1>

<general_tags>
<count>1girl, solo</count>
<artists>ciloranko, kazutake hazano, onineko, r17329 illu, ma1ma1helmes b illu</artists>
<style>anime_style, digital_art</style>
<background>detailed_background, scenery, detailed_background</background>
<atmosphere>cheerful</atmosphere>
<lighting>dynamic_angle, depth_of_field, high_contrast, colorful, detailed_light, light_leaks, beautiful_detailed_glow, best_shadow, shiny_skin, cinematic_lighting, ray_tracing</lighting>
<quality>HDR, 8K, masterpiece, best quality, amazing quality, very aesthetic, extreme aesthetic, detailed eyes, sharp eyes, newest, highres, absurdres, incredibly absurdres, very awa, detailed backgroud, finished, overlapping, appropriate posture, appropriate configuration, cropping, thick dense skin, ultra-precise skin, soft cheeks</quality>
<objects>bag</objects>
</general_tags>

Token usage: Calculating...

Negative Prompt

<danbooru_tags>low_score_rate, worst quality, low quality, bad quality, lowres, low res, pixelated, blurry, blurred, compression artifacts, jpeg artifacts, bad anatomy, worst hands, deformed hands, deformed fingers, deformed feet, deformed toes, extra limbs, extra arms, extra legs, extra fingers, extra digits, extra digit, fused fingers, missing limbs, missing arms, missing fingers, missing toes, wrong hands, ugly hands, ugly fingers, twisted hands, flexible deformity, conjoined, disembodied, text, watermark, signature, logo, ugly, worst, very displeasing, displeasing, error, doesnotexist, unfinished, poorly drawn face, poorly drawn hands, poorly drawn feet, artistic error, bad proportions, bad perspective, out of frame, ai-generated, ai-assisted, stable diffusion, overly saturated, overly vivid, cross-eye, expressionless, scan, sketch, monochrome, simple background, abstract, sequence, lineup, 2koma, 4koma, microsoft paint \(medium\), artifacts, adversarial noise, has bad revision, resized, image sample,low_aesthetic</danbooru_tags>

System Prompt

Height

512 2048

Width

512 2048

Inference Steps

1 100

Guidance Scale

1 20

Sigmas Factor

Lower values increase detail and complexity. Higher values simplify and clean the image.

0.9 1.1

Seed (-1 for random)

Generated Image

Used Seed

Example Prompts

✨ Pony v7 AuraFlow

Generate images from text prompts using the AuraFlow model.

Prompt

Negative Prompt

Height

512 1536

Width

512 1536

Inference Steps

1 100

Guidance Scale

1 20

Sigmas Factor

0.95 1.05

Seed (-1 for random)

Generated Image

Used Seed

🌌 NetaYume v3.5 Lumina

Generate images from text prompts using the Lumina 2 model with a focus on anime aesthetics.

Prompt

Negative Prompt

System Prompt

Height

512 2048

Width

512 2048

Guidance Scale (CFG)

1 10

Sampling Steps

10 100

CFG Truncation Ratio

0 10

Sigmas Factor

0.9 1.1

CFG Normalization

Seed (-1 for random)

Generated Image

Used Seed