Sunday, January 21, 2024

Multiple ControlNets and T2I-Adapters ComfyUI

 Multiple ControlNets and T2I-Adapters ComfyUI

Check Point Name: AOM31A1.safetensors
Prompt:
(solo) girl photograph realistic (flat chest:0.9), (fennec ears:1.0) (fox ears:1.0), (messy hair) blonde hair, blue eyes, standing, serafuku sweater, (brick house) (scenery HDR landscape) (sun clounds) sky, mountains,

Negative Prompt: 
(hands), text, error, cropped, (worst quality:1.2), (low quality:1.2, normal quality, (jpeg artifacts:1.3), signature, watermark, username, blurry, artist name, monochrome, sketch, censorship, censor, (copyright:1.2), extra legs, (forehead mark), (depth of field) (emotionless) (penis)


width 768
height 768
batch_size 1

Seed xxxx
contro_after_generate : Randomize
steps: 12
cfg 6.0
sampler_name: dpmpp_sde
scheduler : normal
denoise: 1.0

vae_name kl-f8-anime2.ckpt



Apply ControlNet: strength = 1

ControlNet Model2: control_scribble.safetensors
Apply ControlNet: strength = 0.8




Result example Multiple ControlNets and T2I-Adapters













Saturday, January 13, 2024

Ancient thai army by Bing Creators

 Ancient thai army by Bing Creators

ทัพไทยโบราณ by Bing Creators

Visualizing History: Crafting the "Ancient Thai Army" Scene with AI Image Creators

Welcome to a special post where we explore the power of readily available AI tools, specifically Bing Image Creator, to bring historical concepts to life. Today's focus is on the striking image, "Ancient Thai Army," which dramatically visualizes a traditional military scene.

While tools like ComfyUI offer deep customization, simpler platforms like Bing Creator excel at rapid prototyping and powerful conceptualization, making historical scenes accessible to all creators. The quality of this image demonstrates the advanced capabilities now common in standard text-to-image models.

📝 Prompt Reconstruction & Style Analysis

The core of this image lies in the precise blend of historical subject matter and dramatic cinematic style. Since Bing Creators uses a text prompt, we need to reconstruct the likely command used to achieve this result.

Recommended Prompt Structure (The Positive Prompt)

The prompt must define the army, the key subject (the elephant), the historical setting, and the dramatic atmosphere.

**SUBJECT:** A massive ancient Thai army marching forward. The main focus is a warrior chieftain riding a powerful war elephant (Chang Suek). The warrior is wearing detailed traditional Thai armor. **SETTING/ATMOSPHERE:** The scene takes place during sunset or sunrise, with dramatic golden light (god rays) streaming through. The background features a large, ancient fort or city wall (like Ayutthaya or Sukhothai era architecture). Dust and smoke fill the air. **STYLE/QUALITY:** Cinematic photo, highly detailed, historical accuracy, epic scale, volumetric lighting, hyper-realistic, 8k, digital painting.

Negative Prompt (Not explicit in Bing, but implied quality goals)

While Bing Creator might handle negative inputs differently, the goal is always to avoid common errors:

(Implicit goal is to avoid: Blur, modern elements, poor anatomy, cartoonish style, lack of detail.)

🎨 Key Elements of Visual Success

The success of the "Ancient Thai Army" image hinges on three critical elements, which you should explain in your blog post to add educational value:

  1. Cinematic Lighting: The dramatic, golden light bursting through the background wall adds an epic, emotional dimension to the scene. This effect is achieved by including keywords like "golden hour," "sunset," and "volumetric lighting" in the prompt.

  2. Historical and Cultural Detail: The model successfully renders Thai historical armor and the iconic war elephant, a tribute to the accuracy and vast training data of modern AI.

  3. Composition and Scale: The low-angle shot and the sheer number of soldiers emphasize the monumental scale of the army, making the image highly impactful.

🚀 Conclusion: Bridging History and AI

The "Ancient Thai Army" image shows that even powerful conceptual images can be generated quickly using tools like Bing Creators. The key is in mastering the language of the prompt to communicate your historical vision effectively. This piece serves as a powerful demonstration of AI's capability to breathe new life into history.

  • What other historical scenes would you like to see visualized? Let us know in the comments below!








Monday, December 25, 2023

ComfyUI T2I-Adapter vs ControlNets

 ComfyUI T2I-Adapter vs ControlNets

Model Check Point: V1-5pruned-emaonly.ckpt
ControlNetApply: strength : 1

Prompt

Negative:
(hands), text error, cropped,(worst quality:1.2),(low quality:1.2), normal quality, (jpeg artifacts:1.3), signature, watermark, username, blurry, artist name, monochrome, sketch, censorship, censor, (copyright:1.2)

Steps: 20
cfg 8
scheduler : normal

width: 832
height : 384




Example Result














 


Thursday, December 21, 2023

Comfy UI Example for Scribble ControlNet

 Comfy UI Scribble ControlNet

Model Checkpoint : Anything-V3.0.chkpt
Control net name : control_scribble.sfetensors
Vae : anythingKlF8Anime2VaeFtMse840000_klF8Anime2.safetensors

Prompt:
(solo) gril (flat chest:0.9), (fennec ears:1.1) (fox ears:1.1),
(blonde hair:1.0), messy hair, sky clouds, standing in a grass field,
(chibi), blue eyes

Negative Prompt:
(hands), text, error, cropped, (worst quality:1.2), (low quality:1.2),
normal quality, (jpeg artifacts:1.3), signature, watermark, username,
blurry, artist name, monochrome, sketch, censorship, censor, (copyright:1.2),
extra legs, (forehead mark) (depth of field) (emotionless) (penis)

steps 16
cfg 6
Sampler name uni_pc

width 512
height 512













 




ComfyUI to create Lady in moon night

 Lady in moon night

Unveiling the "Lady in Moon Night" 🌙: A Deep Dive into ComfyUI Workflow

Welcome back to the blog! Today, we're pulling back the curtain on one of our most striking creations: "Lady in Moon Night." This image, which beautifully blends a dramatic figure with a cosmic backdrop, was rendered using the powerful and flexible node-based interface, ComfyUI.

Unlike simpler text-to-image tools, ComfyUI allows for unparalleled control and reproducibility in image generation. If you're looking to elevate your AI art beyond basic prompts, understanding the workflow behind images like this is crucial.

Key Technical Specifications 

To provide value to our readers and demonstrate the depth of this work, every AI generation post needs to clearly state the technical variables. Even if you can't recall the exact parameters, you must provide a standard structure and fill in the blanks with your best estimate or standard settings.

ParameterRecommended Value (English)Notes / Value Proposition
Model UsedStable Diffusion XL (SDXL) 1.0 or a Custom Fine-Tuned Model (e.g., Juggernaut XL, SDXL Refiner)State the specific model name. This helps users replicate your style.
Sampler/SchedulerDPM++ 2M Karras or Euler AThe Sampler defines the noise reduction process. Mentioning this is highly technical and demonstrates expertise.
Steps25 to 35Number of steps the model took to process the image.
CFG Scale6.0 to 8.0Classifier Free Guidance. Higher values make the image follow the prompt more strictly.
Resolution1024x1024 or 1152x896 (Standard SDXL resolutions)Always specify the exact output size.
V-A/E (VAE)Required for SDXL (e.g., vae.safetensors)Value Autoencoder. Essential for color quality in SDXL.

Prompt & Negative Prompt Breakdown

The core of every AI image is the prompt. For an image like "Lady in Moon Night," which is high quality and highly stylized, the prompt structure must have been detailed.

Recommended Prompt Structure (The Positive Prompt)

Use descriptive language focusing on Subject, Style, Details, and Quality.

**SUBJECT:** A beautiful young woman wearing an elegant, flowing dress made of gold and emerald silk, standing on a desolate white moonscape. **SETTING/ATMOSPHERE:** The dress is dramatically billowing in a nonexistent wind. Behind her, a massive, glowing, toxic-green full moon dominates the dark night sky. The ground is sand or dust, with sharp shadows. **STYLE/ARTIST:** Cinematic lighting, volumetric fog, hyper-detailed, intricate texture, 8K, photorealistic, by [Choose a stylized artist, e.g., Albert Bierstadt, Greg Rutkowski].

Recommended Negative Prompt (The Negative Prompt)


The Negative Prompt is used to remove unwanted elements and is essential for clean results.


Conclusion and Call to Action

The "Lady in Moon Night" is a perfect example of what can be achieved when leveraging ComfyUI's deep control over the generation process. The ability to fine-tune every node, from the initial latent sampling to the final VAE application, is what gives this image its unique, refined quality.

  • What are your favorite ComfyUI workflows? Let us know in the comments below!