Fantasy Vision DiT | TA Exclusive

CHECKPOINT
Original - TenStar Fund


Updated:

11K

Fantasy Vision Model Overview

I’m excited to introduce my latest checkpoint model, based on HunyuanDiT-v1.2. This model has been trained over 60,000 steps to ensure the generation of high-quality fantasy-themed images with vibrant details images.

Model Details :

  • Type: Photorealistic model/fantasy-themed/vibrant details

  • Trigger Words: None required

  • Chinese language support: No

  • Output: High-detail, high-resolution images that closely resemble real-life photographs

Configuration Used for Training:

  • GPU: A6000

  • Dataset: Combination of 2 stock photos and my own custom dataset

  • Batch Size: 1

  • Optimizer: AdamW

  • Scheduler: Cosine

  • Learning Rate: 1e-5

  • Epochs: Target of 100 epochs

  • Captioning: GPT4

Quick Guide and Parameters V2:

V1 and V2 have some significant changes. For example, V1 had issues with the eyes, which I tried to fix in V2. I also worked on improving color tones and prompt accuracy. As we know, longer prompts don't perform well on DiT, and while I haven't fully resolved that yet, further training might help. So far, it's looking good—one of the best DiT models out there😛

  • VAE: SDXL

  • Sampler: dpmpp_2m

  • Scheduler: sgm_uniform (Recommended for best results) | Karras (Now supported)

  • Sampling Steps: 25+

  • CFG Scale: 7

Quick Guide and Parameters:

  • VAE: SDXL

  • Sampler: dpmpp_2m

  • Scheduler: sgm_uniform (Recommended for best results)

  • Sampling Steps: 25+

  • CFG Scale: 7

Important: Please avoid using NSFW/mature content in your prompts, as it may lead to unreliable results. Additionally, shorter prompts tend to work better with both SD3 and DiT models.

Note:

This is not a merged or modified model. It is the original Realistic Vision fine-tuned model. Some users have been spreading incorrect information in the model's comment section. If you have any questions or want to know more, join my Discord server or share your thoughts in the comment section. Thank you for your time.

Version Detail

HunYuanDiT-v1.2
120000

Project Permissions

Reprinting is strictly prohibited

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated contents

  • Use on generation services

  • Sell this model or merges

Comments

Related Posts

Describe the image you want to generate, then press Enter to send.