thick thighs

sexual situations

physical violence

disturbing

extremist

hanging

hate symbols

nazi party

breasts out

strapless leotard

revealing clothes

weapon violence

emaciated bodies

female swimwear or underwear

male swimwear or underwear

partial nudity

self injury

white supremacy

adult toys

graphic male nudity

illustrated explicit nudity

nudity

sexual activity

graphic violence or gore

graphic female nudity

vore

bestiality

corpses

breast out

one breast out

huge breasts

gigantic breasts

huge butt

wide hips

covered nipples

hair over breasts

no panties

sitting on face

convenient censoring

anal

dildo riding

downblouse

peeing

oral

oral invitation

hentai

porn

bukkake

cumshot

cumdrip

cum in pussy

cum on face

cum on hair

cum on body

cum on tongue

cum on hands

cum in mouth

cum on pussy

eat_cum

fellatio

implied fellatio

after fellatio

triple fellatio

autofellatio

pov fellatio

fucked silly

presenting ass

presenting pussy

spreading legs

spread legs

swimwear

lingerie

bikini

latex clothing

TRPCError

<a target="_blank" rel="ugc" href="https://www.patreon.com/PolyPhaze">PolyPhaze | Generate reality @ PolyPhaze | Patreon</a><h2 id="dream-come-true-v4.2:-advance-your-creativity-with-this-new-update!-uxqtn5gca">Dream Come True v4.2: Advance Your Creativity with this new update!</h2>DCT v4.2 is an evolutionary update to the highly acclaimed v4.0 model and it adds several new features and improvements:- Different approach to model tuning- More photorealistic in many ways and scenarios- Wider range of stable guidance (samplers, schedulers, CFG, steps...) - More ways of image manipulation by better prompt understanding (relatively short and descriptive prompts are now much more effective)In our opinion, the best results can be achieved with the following settings:CGF: 6-9, Samplers: DPM++SDE (35-45st.), DPM++2M SDE Heun (45-50st.), DPM++2S a (35-45st.), Schedulers: Polyexponential or Karras for all recommended samplers.From this moment onwards, the PolyPhaze team will separate the model deployment in two branches, so we suggest you to visit our Patreon page for our latest and greatest model versions(DCT v5.0 has already been deployed, and v5.1 update is currently in testing phase).Some versions of our current and fully updated models will become publicly available at some point in time, when the next capital model upgrade becomes available to our Patreon members.Thank you for your support!

Dream Come True v4.2: Advance Your Creativity with this new update!DCT v4.2 is an evolutionary update to the highly acclaimed v4.0 model and it adds several new features and improvements:- Different approach to model tuning- More photorealistic in many ways and scenarios- Wider range of stable guidance (samplers, schedulers, CFG, steps...) - More ways of image manipulation by better prompt understanding (relatively short and descriptive prompts are now much more effective)In our opinion, the best results can be achieved with the following settings:CGF: 6-9, Samplers: DPM++SDE (35-45st.), DPM++2M SDE Heun (45-50st.), DPM++2S a (35-45st.), Schedulers: Polyexponential or Karras for all recommended samplers.From this moment onwards, the PolyPhaze team will separate the model deployment in two branches, so we suggest you to visit our Patreon page for our latest and greatest model versions(DCT v5.0 has already been deployed, and v5.1 update is currently in testing phase).Some versions of our current and fully updated models will become publicly available at some point in time, when the next capital model upgrade becomes available to our Patreon members.Thank you for your support!

Dream Come True v4.2

This version delivers a significant leap in visual quality. We've improved the realism with richer colors, added depth for a more three-dimensional feel, and crafted detailed backgrounds to bring the scene to life.

Dream Come TrueXL v4.0

Improved colors, poses, and small fixes.

Dream Come True XL v3.0

Dream Come True XL v2.0

DCTXLv1.42

Updates!Enhanced Anatomy and Detail:<ul><li>Expanded Training: Focused training on specific anatomy like noses, ears, armpits, hands, and hand expressions (gestures and signs). This improves the model's ability to generate these elements with greater accuracy and detail. (Note: Work on further refinement is ongoing.)</li><li>Richer Skin Textures: The model is now trained to generate more realistic skin textures including pores, peach fuzz, and beauty marks, adding a new layer of realism to the generated images.</li></ul>Improvements:<ul><li>Clearer Structure: The description is reorganized for better readability.</li><li>Emphasis on Benefits: Focuses on how the new training improves the model's capabilities.</li><li>Transparency: Acknowledges ongoing development for anatomy refinement.</li></ul>

DCTXLv1.311

Hello, everyone!I'm excited to share some updates on the model since the previous versions. We've been listening closely to your feedback and have been hard at work on improvements. While it's still a work in progress, you'll already notice a significant difference:<ul><li>Improved Anatomy: We've focused on refining anatomical accuracy, particularly in areas like [mention specific areas].</li><li>Reduced Text/Signatures: We're actively working on removing text and signatures from generated images. We've already seen a [mention percentage] reduction, and we're committed to getting this to 100%.</li><li>Enhanced Posing: The model now handles a wider range of poses with greater naturalism.</li><li>More Realistic Skin Textures: Skin textures are now more detailed, incorporating features like pores and blemishes for added realism.</li><li>Natural Hands and Clothing: We've improved the generation of hands and clothing, achieving more natural appearances even without extensive prompting.</li></ul>Looking Ahead:We're also focusing on addressing some remaining challenges:<ul><li>Image Clarity and Details: We're retraining the model with a dataset of significantly higher resolution images (3000x2000). This will help generate sharper images with finer details.</li><li>Color and Contrast: We're working on providing the model with a broader range of color palettes and contrast levels to create more visually appealing outputs.</li><li>Scene Lighting: The model is being trained on a wider variety of lighting scenarios to improve its ability to handle different lighting conditions.</li><li>Full Body Shots: We're incorporating more high-resolution images with complete figures to address detail and limb issues in full-body images.</li><li></li></ul>We appreciate your continued feedback and support!

DCTXLv1.2

DCT(Dream Come True) XL

DCT v3.0 SD1.5

DCT(Dream Come True) SD15

DCT(Dream Come True) SDXL and SD1.5

00070-655068531.png

Type	Checkpoint Trained
Stats	815
Reviews	Very Positive (61)
Published	Apr 4, 2024
Base Model	SDXL 1.0
Training	Steps: 40 Epochs: 30
Usage Tips	Clip Skip: 2
Hash	AutoV2 82F0724571