♦♦Pearly Desire♦♦

An experimental merge of Opal and Anima mix, This one tries to bring a more detailed result while still leaning towards a more comic like feel especially in the clothing. Long detailed prompts get the best results,

♦♦Installing for local gen♦♦

Get the text encoder and VAE from the HuggingFace page.

The model is natively supported in ComfyUI. The model files go in their respective folders inside your model directory:

• Pearly Opal Anima .safetensors goes in ComfyUI/models/diffusion_models

• qwen_3_06b_base.safetensors goes in ComfyUI/models/text_encoders

• qwen_image_vae.safetensors goes in ComfyUI/models/vae (this is the Qwen-Image VAE, you might already have it)

♦♦Settings♦♦

Settings that i use with this checkpoint

Note: I’m pretty much winging it.

1st Ksampler

• Sampler: er_sde

• Scheduler: Simple

• CFG: 5 ish

• Steps: 20 - 35

Ultimate SD Upscaler

• Sampler: er_sde

• Scheduler: Simple

• CFG: 5 ish

• Steps: 5 - 20

• Tile size: 512 or 1024

Recommended positives:

(masterpiece, best quality, good quality, score_9, score_8),

Recommended negatives:

(lowres, bad quality, worst quality, long neck, bad , watermark, jpeg artifacts, ugly,  score_1, score_2, score_3), , 

Additional notes:

This model performs best with more detailed prompts. Dont forget you can also use weights on prompts example: (standing:1.2),