realDream_sdxlPony13

Prompt

spider Gwen,blonde,female superhero,very beautiful,red and black and white costume,[photorealistic, realistic],blue eyes,teen,pink highlights,roof top of a building background,

Negative Prompt

empty background,hrd nipples,nsfw,nude,(piercing),anime,cartoon,

Prompt

score_9, score_8_up, score_7_up, score_6_up, score_5_up, (realistic:1.4), 1girl, necklace, lips parted, seductive eyes, brown hair, turquoise tank top, (detailed face and eyes:1.2), fair skin, freckles, Lara Croft, tactical cargo shorts, black background, wet, c-cup breasts, looking at viewer, vibrant colors, sexy, cute, tiny waist, no makeup, wet, Caucasian, British, chest up photo, closeup headshot, wide hips

Negative Prompt

score_6, score_5, score_4, source_pony, (worst quality:1.2), (low quality:1.2), (normal quality:1.2), lowres, bad anatomy, bad hands, signature, watermarks, ugly, imperfect eyes, skewed eyes, unnatural face, unnatural body, error, extra limb, missing limbs, bangs, hair strands, CyberRealistic_Negative_PONY, words, letters, muscular, wrinkles, folds

Prompt

score_9, score_8_up, score_7_up,moon Night scenery, outdoors, tree, no humans, sky, day, reflective water, snow, cloud, blue sky, water, building, winter, bridge, bare tree, river, mountain, Castle, winter, reflection, Iced river, high detailed , extremely detailed, caustics, dynamic lighting, fisheye lens, hyperrealistic, no humans, very wide shot, moon Night <lora:Fant5yP0ny:0.5> <lora:cfg_scale_boost:0.4>

Negative Prompt

score_4,score_5,score_6, deep_negative_pony

Model description

On my Patreon I am sharing beta versions of the models I develop. Most of them are shared in the free section, but consider joining my Patreon as a contributor if you like the project and would like to help me acquire more computing power. The Patreon price is the cheapest the platform allows. Currently my computer does not have the full capacity to work with Flux and with more sophisticated models that will come in the future. Also my country is protectionist in the economy and charges a lot of taxes on computers and hardware parts.

Real Dream Website (Faster download)

Help me destroy abstract art once and for all 👇

Help me buy some new hardware and computation power. (Patreon)

Available at TensorArt: https://tensor.art/models/764428935426615833

Available as an API service on Segmind

Stable Diffusion prompt generator AI Tool Bot: https://hf.co/chat/assistant/65c5622d649836a37deb39f6

Stable Diffusion guide AI Tool Bot (You can ask in your native language):

https://hf.co/chat/assistant/6650e6182682ff777fcf0d38

Recomendations:

Default SD 1.5: Use the "DPM++ SDE Karras" or "DPM++ 2M Karras" sampler with only 20 steps for better quality. "DPM++ SDE Karras" has better quality but is slow.

Default SD 1.5: Use the CFG scale between 5 and 9. CFG scale at 5 is recommended. Stable Diffusion default value is 7.

SD 1.5 LCM: Use the "Euler a" or "LCM" sampler with only 8 steps for better quality.

SD 1.5 LCM AND SDXL Lightning: Use the CFG scale between 1 and 2. CFG scale at 2 is recommended.

Pony SDXL: Use the "Euler a" or "DPM++ SDE Karras" sampler with 20-30 steps for better quality.

LCM with DPM++ SDE Karras: Sampling steps 8, Hires. Fix enabled, upscaler latent, Hires steps 2, hires. denoise 0.45, upscale by 1.05, cfg scale 1.5.

LCM with DPM++ 2M Karras: Sampling steps 8, Hires. Fix enabled, upscaler latent, Hires steps 2, hires. denoise 0.55, upscale by 1.05, cfg scale 1.5.

SD 1.5: Resolution between 512 and 768 using "Hires. Fix" or other form of upscaling. The 600x600 resolution is the one that has worked best.

If you use "Hires. Fix", use "Upscale by" with the value 1.5 with denoising at 0.6.

Tips for a better prompt:

Use (word) for larger weight and [word] for smaller weight and word:0.5 to set the weight manually.

Recomendations for improvement on performance (Stable Diffusion Web UI):

Use Token Merging Ratio 0.5 on optimization settings.

If you have a GPU with low VRAM, use --medvram or --lowvram on command line arguments (webui-user.bat on Windows).

Enable fp8 in the latest versions of Web UI to save a lot of ram. It can speed up SDXL a lot depending on how much ram and vram you have.

If you are having a lot of trouble running SDXL in the Web UI. Try using Fooocus

Extensions I recommend: Controlnet, Booru tag autocompletion, CivitAI Browser+,Ultimate SD Upscale,Lobe Theme

Recommended negative prompts to improve human images: amputee, deformed body, long neck, extra fingers, bad body proportions, mutated hands, mutilated, mutation, ugly, fused fingers, malformed limbs, extra heads, disfigured,

I would like to thank the following projects that were important to the community and helped improve Stable Diffusion to achieve greater levels of realism:

Realistic Vision

RealVisXL

epiCRealism

epiCPhotoGasm

QGO

ICBINP

Analog Madness

majicMIX realistic

CyberRealistic

Juggernaut

LCM Lora

SDXL Lightning

Fast Pony Merge

Real Pony

Pony Realism

Osorubeshi Pony

Sevenof9 Pony

Sat Pony

Stallion Pony

Special thanks to other projects from anime and artistic models:

Pony Diffusion

AutismMix SDXL

T-ponynai3

Prefect Pony XL

The use of Real Dream models in API services, depending on me, is allowed as long as it follows the ethical use rules at the end of the description. If you provide it as an API service, please also disclose the rules.

This model is capable of generating very realistic images that can confuse people's critical sense, please do not use it irresponsibly, harming ordinary people or public figures. Also avoid its use in electoral campaigns, promoting or damaging the image of candidates. Although the field of artificial intelligence is poorly regulated, its improper use can cause legal penalties even in countries with little regulation in the area. Be very careful to not commit crimes in your country and not to promote injustices against innocent people. I do not authorize the use of this model for Lora training using the face of real people without authorization from the biological owner. I do not authorize the use of images generated by this model for scam applications and the dissemination of false information. If the image is not included in the cases of unauthorized use but for some reason may cause confusion among the public and may end up being considered true, causing some form of misinformation, place a notice that the image is generated by AI.

I do not allow the upload of any of my models on Tensor Art. I only do not allow it there because the policy of duplicate models on Tensor Art prevents me from uploading again if someone has already done it.

As it is unfeasible to moderate all NSFW posts using real people's Loras. I have enabled to automatically hide all NSFW posts.

Trigger words

You should use None to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.