Pipeline Guide

360 Hextile supports multiple AI processing pipelines, each optimized for different use cases. This guide helps you choose the right pipeline and understand how they work.

Available Pipelines

1. Stable Diffusion 1.5

Best for: Lower VRAM systems and extensive ControlNet/LoRA ecosystem

Technical Details: - Model: Stable Diffusion 1.5 Inpainting - Type: Tiled (uses hexagonal projection) - VRAM: ~4-6GB - Native tile size: 512×512 - Processing: Sequential or batch modes

Features: - ✅ Positive and negative prompts - ✅ Extensive ControlNet support (8 types: Canny, Depth, OpenPose, Scribble, MLSD, Seg, Normal, Lineart) - ✅ LoRA support (largest ecosystem) - ✅ Cardinal direction prompts (6 directions) - ✅ Template-based hexagonal tiling - ✅ Low VRAM requirements

When to Use: - Have limited GPU memory (4-6GB) - Need ControlNet for structural guidance - Want access to vast LoRA library - Processing on older or mid-range GPUs

Example Configuration:

{
  "pipeline": "sd15_inpaint",
  "model": "stable-diffusion-v1-5/stable-diffusion-inpainting",
  "template": "Hextile_32_3K",
  "global_prompt": "fantasy landscape with magical elements",
  "negative_prompt": "blurry, low quality, distorted",
  "strength": 0.8,
  "guidance_scale": 7.5,
  "num_inference_steps": 30,
  "controlnet": {
    "enabled": true,
    "type": "canny",
    "strength": 0.85
  }
}

2. Stable Diffusion 2.1

Best for: Higher resolution tiles with ControlNet support

Technical Details: - Model: Stable Diffusion 2.1 Inpainting - Type: Tiled (uses hexagonal projection) - VRAM: ~4-6GB (512px) or ~6-8GB (768px) - Native tile size: 512×512 (Inpainting) or 768×768 (Base) - Processing: Sequential or batch modes

Features: - ✅ Positive and negative prompts - ✅ ControlNet support (4 types: Canny, Depth, OpenPose, Scribble) - ✅ LoRA support (SD2.1-specific) - ✅ Cardinal direction prompts (6 directions) - ✅ 768px native resolution option - ✅ Template-based hexagonal tiling

When to Use: - Need higher resolution tiles than SD1.5 - Want improved image quality over SD1.5 - Need ControlNet with moderate VRAM - Using SD2.1-specific LoRAs

Model Variants: - SD 2 Inpainting (512px): Best for hexagonal tiles, lower VRAM - SD 2.1 Base (768px): Higher quality, more VRAM required

Example Configuration:

{
  "pipeline": "sd21_inpaint",
  "model": "sd2-community/stable-diffusion-2-inpainting",
  "template": "Hextile_32_3K",
  "global_prompt": "realistic landscape with mountains",
  "negative_prompt": "blurry, low quality, distorted",
  "strength": 0.8,
  "guidance_scale": 7.5,
  "num_inference_steps": 30,
  "controlnet": {
    "enabled": true,
    "type": "depth",
    "strength": 0.85,
    "preprocessor": {
      "depth": {
        "boost": 1.5
      }
    }
  }
}

3. SDXL Inpainting

Best for: General-purpose 360° AI generation with proven quality, no ControlNet needed

Technical Details: - Model: Stable Diffusion XL 1.0 or SDXL-Turbo - Type: Tiled (uses hexagonal projection) - VRAM: ~12GB (both models) - Processing: Sequential or batch modes - Speed: Moderate (SDXL) or Fast (Turbo)

Features: - ✅ Positive and negative prompts - ✅ LoRA support - ✅ Cardinal direction prompts (6 directions) - ✅ Strength, guidance scale, inference steps controls - ✅ Template-based hexagonal tiling - ✅ NEW: Model selection (SDXL 1.0 or SDXL-Turbo) - ❌ No ControlNet (not in current version)

When to Use: - Standard 360° image enhancement - Want negative prompt control - Familiar with Stable Diffusion parameters - Need proven, stable results - Want fast iteration (use Turbo model)

Example Configuration (Standard SDXL 1.0):

{
  "pipeline": "sdxl_inpaint",
  "model": "diffusers/stable-diffusion-xl-1.0-inpainting-0.1",
  "template": "Hextile_32_3K",
  "global_prompt": "vibrant landscape with mountains and lake",
  "negative_prompt": "blurry, low quality, distorted",
  "strength": 0.66,
  "guidance_scale": 7.5,
  "num_inference_steps": 50,
  "interpolation": "6CardinalDirections",
  "cardinal_prompts": {
    "front": "mountain peaks",
    "back": "serene lake",
    "left": "pine forest",
    "right": "rocky cliffs",
    "above": "clear blue sky",
    "below": "lush grass"
  }
}

Example Configuration (SDXL-Turbo for Speed):

{
  "pipeline": "sdxl_inpaint",
  "model": "local/sdxl-turbo",
  "template": "Hextile_32_3K",
  "global_prompt": "vibrant landscape with mountains and lake",
  "negative_prompt": "blurry, low quality, distorted",
  "strength": 0.66,
  "guidance_scale": 0.0,
  "num_inference_steps": 1,
  "interpolation": "6CardinalDirections"
}

4. SD 3.5 Inpainting

Best for: Latest Stable Diffusion technology with quality/speed modes

Technical Details: - Model: Stable Diffusion 3.5 Large or Large-Turbo - Type: Tiled (uses hexagonal projection) - VRAM: ~12-16GB - Processing: Sequential or batch modes - Speed: Turbo is very fast, Large is moderate

Features: - ✅ Model selection (Turbo for speed, Large for quality) - ✅ LoRA support (SD3-specific LoRAs) - ✅ Cardinal direction prompts (6 directions) - ✅ Native 1024×1024 resolution support - ✅ Template-based hexagonal tiling - ✅ Auto-scheduler switching (Turbo vs Standard) - ❌ No negative prompt (SD3 architecture doesn't use them effectively) - ❌ No ControlNet (not supported)

When to Use: - Want latest SD technology (MMDiT architecture) - Need fast iteration with Turbo mode - Want quality mode for final renders - Don't need negative prompts - Have 12-16GB VRAM available

Example Configuration (SD3.5-Turbo for Speed):

{
  "pipeline": "sd35_inpaint",
  "model": "stabilityai/stable-diffusion-3.5-large-turbo",
  "template": "Hextile_32_3K",
  "global_prompt": "vibrant landscape with mountains and lake",
  "strength": 0.66,
  "guidance_scale": 1.0,
  "num_inference_steps": 4,
  "interpolation": "6CardinalDirections",
  "cardinal_prompts": {
    "front": "mountain peaks",
    "back": "serene lake",
    "left": "pine forest",
    "right": "rocky cliffs",
    "above": "clear blue sky",
    "below": "lush grass"
  }
}

Example Configuration (SD3.5-Large for Quality):

{
  "pipeline": "sd35_inpaint",
  "model": "stabilityai/stable-diffusion-3.5-large",
  "template": "Hextile_32_3K",
  "global_prompt": "vibrant landscape with mountains and lake",
  "strength": 0.66,
  "guidance_scale": 5.0,
  "num_inference_steps": 40,
  "interpolation": "6CardinalDirections"
}

Model Selection: - SD3.5-Large-Turbo: 1-8 steps (optimal 4), guidance 0-3.5 (optimal 1.0) - SD3.5-Large: 20-50 steps (optimal 40), guidance 3.5-7.5 (optimal 5.0)

Key Differences from SDXL: - Turbo mode is 10-15x faster - No negative prompt field (SD3 architecture doesn't use it) - Auto-scheduler switching (EulerAncestral for Turbo, DDIM for Large) - Separate LoRA directory (sd3-loras/ vs stable-diffusion-loras/)

5. Qwen-Image

Best for: Instruction-based editing and highest-capability image generation

Technical Details: - Model: Qwen2.5-VL / Qwen-Image (20B parameter MMDiT transformer) - Type: Tiled (uses hexagonal projection) - VRAM: ~13GB (GGUF Q4) or ~48GB (BF16 full precision) - Native tile size: 1024×1024 - Processing: Sequential or batch modes

Features: - ✅ Two modes: Generate (text-to-image) and Edit (image-to-image with instruction) - ✅ GGUF Q4 quantization (13GB, recommended for most setups) - ✅ BF16 full precision (48GB, for maximum fidelity) - ✅ ControlNet Union support - ✅ Cardinal direction prompts (6 directions) - ✅ Template-based hexagonal tiling - ✅ Instruction-following edits ("remove the trees", "make the sky dramatic") - ❌ No LoRA support (model weights are self-contained) - ❌ No negative prompt (not applicable to this architecture)

When to Use: - Want instruction-based editing ("turn the sky into a stormy sky") - Need highest available generation capability - Performing complex scene transformations - Have 13GB+ VRAM (GGUF Q4) or 48GB+ (BF16)

Generate Mode — text-to-image from a prompt:

{
  "pipeline": "qwen_image",
  "mode": "generate",
  "model": "Qwen/Qwen2.5-VL-7B-Instruct-GGUF",
  "template": "Hextile_32_3K",
  "global_prompt": "an ancient temple surrounded by jungle at golden hour",
  "strength": 1.0,
  "guidance_scale": 5.0,
  "num_inference_steps": 30
}

Edit Mode — instruction-based image editing:

{
  "pipeline": "qwen_image",
  "mode": "edit",
  "model": "Qwen/Qwen2.5-VL-7B-Instruct-GGUF",
  "template": "Hextile_32_3K",
  "global_prompt": "replace the cloudy sky with a dramatic sunset",
  "strength": 0.75,
  "guidance_scale": 5.0,
  "num_inference_steps": 30,
  "interpolation": "6CardinalDirections",
  "cardinal_prompts": {
    "above": "brilliant orange and pink sunset clouds"
  }
}

GGUF vs BF16: - GGUF Q4 (13GB): Recommended. Minimal quality loss vs full precision, runs on a single 16GB GPU. - BF16 full precision (48GB): Maximum fidelity. Requires multi-GPU or 48GB+ VRAM.

6. TeleStyle

Best for: Highest-quality diffusion-based style transfer

Technical Details: - Model: Qwen-Image-Edit with TeleStyle LoRA - Type: Tiled (uses hexagonal projection) - VRAM: ~13GB (GGUF Q4) - Native tile size: 1024×1024 - Processing: Sequential or batch modes - License: Apache 2.0

Features: - ✅ Diffusion-based style transfer (not neural style transfer) - ✅ Preserves scene structure while applying style - ✅ GGUF Q4 quantization (13GB, same VRAM as Qwen-Image) - ✅ Cardinal direction prompts (6 directions) - ✅ Template-based hexagonal tiling - ✅ Style LoRA built-in (no manual LoRA management) - ❌ No ControlNet - ❌ No negative prompt

When to Use: - Want to apply a consistent artistic style to a 360° scene - Need structure-preserving style transfer (architecture, landscapes) - Working from a reference style (painterly, sketch, cinematic) - Have 13GB VRAM available

Example Configuration:

{
  "pipeline": "telestyle",
  "model": "TeleAI/TeleStyle-GGUF",
  "template": "Hextile_32_3K",
  "global_prompt": "oil painting style, impressionist brushwork, warm palette",
  "strength": 0.8,
  "guidance_scale": 5.0,
  "num_inference_steps": 30,
  "interpolation": "6CardinalDirections"
}

Style Prompt Tips: - Be explicit about the target style: "watercolor illustration", "pencil sketch", "cinematic photography" - Add quality descriptors: "high detail", "professional", "masterful" - Avoid conflicting style instructions within a single pass

7. FLUX.1 Schnell

Best for: Ultra-fast generation with flow matching architecture

Technical Details: - Model: FLUX.1 Schnell by Black Forest Labs - Type: Tiled (uses hexagonal projection) - VRAM: ~12GB - Native tile size: 1024×1024 - Processing: Sequential or batch modes - License: Apache 2.0

Features: - ✅ Ultra-fast 4-step generation via flow matching - ✅ High-quality output in minimal inference steps - ✅ Cardinal direction prompts (6 directions) - ✅ Template-based hexagonal tiling - ✅ Apache 2.0 licensed (fully open) - ❌ No LoRA support - ❌ No ControlNet - ❌ No negative prompt

When to Use: - Need fastest possible generation - Rapid iteration and previewing - Want open-source (Apache 2.0) pipeline - Have 12GB VRAM available

Example Configuration:

{
  "pipeline": "flux_schnell",
  "model": "black-forest-labs/FLUX.1-schnell",
  "template": "Hextile_32_3K",
  "global_prompt": "vibrant mountain landscape at golden hour",
  "strength": 0.8,
  "num_inference_steps": 4,
  "interpolation": "6CardinalDirections"
}

8. FLUX.2 Klein

Best for: Strong prompt adherence with compact model size

Technical Details: - Model: FLUX.2 Klein 4B by Black Forest Labs - Type: Tiled (uses hexagonal projection) - VRAM: ~13GB - Native tile size: 1024×1024 - Processing: Sequential or batch modes - License: Apache 2.0

Features: - ✅ Compact 4B parameter transformer - ✅ Qwen3 text encoder for superior prompt understanding - ✅ Cardinal direction prompts (6 directions) - ✅ Template-based hexagonal tiling - ✅ Apache 2.0 licensed (fully open) - ❌ No LoRA support - ❌ No ControlNet - ❌ No negative prompt

When to Use: - Want excellent prompt adherence - Need a compact but capable model - Want open-source (Apache 2.0) pipeline - Have 13GB VRAM available

Example Configuration:

{
  "pipeline": "flux2_klein",
  "model": "black-forest-labs/FLUX.2-klein-4B",
  "template": "Hextile_32_3K",
  "global_prompt": "ancient temple surrounded by jungle at golden hour",
  "strength": 0.8,
  "num_inference_steps": 30,
  "interpolation": "6CardinalDirections"
}

9. Post Process Passthrough

Best for: Applying post-processing effects without any AI diffusion

Technical Details: - Type: Identity processor — passes image through unchanged before post-processing effects - VRAM: 0 GB (no AI model loaded) - Processing: Instant (no inference)

Features: - ✅ Full post-processing effects stack (color grading, sharpening, vignette, etc.) - ✅ Zero VRAM usage - ✅ Instant processing - ✅ Compatible with all templates - ❌ No AI generation or editing - ❌ No prompts

When to Use: - Want to apply post-processing effects to an already-processed image - Testing post-processing settings without re-running expensive AI inference - Batch-applying color grades or effects to a set of finished images - Working on color correction or export without touching AI output

10. Format Converter

The Format Converter is a specialized tool for converting between 360° projection formats (equirectangular, cubemap, fisheye, and others) without any AI processing.

See the Format Converter guide for full documentation.

Comparison Table

Pipeline Switching

Automatic VRAM Management

The system intelligently manages GPU memory:

Switching Between Diffusion Models:

Currently using: SDXL (12GB in VRAM)
User switches to: Qwen-Image

System automatically:
1. Unload SDXL model
2. Run garbage collection
3. Clear CUDA cache
4. Load Qwen-Image model (13GB)

Result: No OOM crash!

In the UI

1. Click pipeline dropdown in header
2. Select desired pipeline
3. UI updates with appropriate form
4. Previous pipeline automatically unloaded (if diffusion)
5. Config updated with new pipeline

Choosing the Right Pipeline

Decision Tree

Do you need ControlNet?
├─ YES → Use SD 1.5 (8 types) or SD 2.1 (4 types)
└─ NO → Continue...

Do you want style transfer?
├─ YES → TeleStyle (structure-preserving, 12GB)
└─ NO → Continue...

Do you want instruction-based editing?
├─ YES → Qwen-Image Edit mode (13-48GB)
└─ NO → Continue...

How much VRAM do you have?
├─ 4-6 GB → SD 1.5 or SD 2.1
├─ 8-12 GB → SDXL
├─ 12-16 GB → SD 3.5 Turbo or SD 3.5 Large
└─ 13-48 GB → Qwen-Image

Need negative prompts?
├─ YES → SD 1.5, SD 2.1, or SDXL
└─ NO → Any pipeline works

Want maximum speed, no AI?
├─ YES → Post Process Passthrough (0 GB VRAM)
└─ NO → Choose based on quality needs

Need projection conversion?
└─ YES → Format Converter

Use Case Examples

Scenario 1: Enhance a 360° Photo (Quality) - Pipeline: SDXL Inpaint - Model: SDXL 1.0 Inpainting (Default) - Why: Need subtle enhancement with negative prompt control - Settings: Low strength (0.3-0.5), high steps (50-70), guidance 7.5

Scenario 2: Fast Iteration / Previewing - Pipeline: SDXL Inpaint - Model: SDXL-Turbo (Fast) - Why: Quick iterations to test prompts and settings - Settings: Medium strength (0.5-0.8), 1-4 steps, guidance 0.0 - Tip: Iterate with Turbo, then final render with SDXL 1.0

Scenario 3: Instruction-Based Scene Edit - Pipeline: Qwen-Image (Edit mode) - Why: Natural language instructions like "make the forest look like autumn" - Settings: Medium strength (0.6-0.8), 30 steps, GGUF Q4 model

Scenario 4: Artistic Style Transfer - Pipeline: TeleStyle - Why: Apply a consistent painterly or illustrative style while preserving structure - Settings: Medium-high strength (0.7-0.85), 30 steps

Scenario 5: Rapid Prototyping Workflow - Step 1: SDXL-Turbo (test 5-10 prompt variations, 1 step each) - Step 2: SDXL 1.0 (final render with best prompt, 50 steps) - Why: 10-30x faster iteration before final quality render

Scenario 6: Post-Processing Only - Pipeline: Post Process Passthrough - Why: Apply color grades or effects to a completed AI image without re-running inference - Settings: No strength/steps — effects only

Parameter Guidelines

SDXL Inpaint

Model Selection: - SDXL 1.0 Inpainting (Default): Best quality, standard settings - SDXL-Turbo (Fast): 10-30x faster, requires different settings

Strength (0.0 - 1.0): - 0.0-0.3: Subtle enhancement, keep original details - 0.4-0.7: Moderate transformation - 0.8-1.0: Heavy transformation, more creativity

Guidance Scale (0.0 - 20.0): - For SDXL 1.0: - 5.0-7.0: More creative, less prompt adherence - 7.5-10.0: Balanced (recommended) - 10.0-15.0: Strict prompt following - 15.0+: Very strict, may reduce quality - For SDXL-Turbo: - 0.0: Required! (Turbo is trained without guidance) - Any value > 0 will degrade quality

Inference Steps: - For SDXL 1.0: - 20-30: Fast, lower quality - 40-60: Balanced (recommended) - 70-100: Highest quality, slow - For SDXL-Turbo: - 1-4: Optimal range (start with 1) - Higher values don't improve quality

Qwen-Image

Strength (0.0 - 1.0): - 0.5-0.7: Subtle instruction-based edits - 0.7-0.85: Standard edits (recommended) - 0.9-1.0: Heavy transformation or full generation

Guidance Scale (1.0 - 10.0): - 3.0-5.0: Balanced (recommended) - 6.0+: Strict instruction adherence

Inference Steps: - 20-25: Fast preview - 28-35: Balanced (recommended) - 40-50: Highest quality

Resolution Controls

Available for SDXL, SD3.5, Qwen-Image, and TeleStyle tiled pipelines.

Output Resolution

Control the final equirectangular output resolution. All presets maintain the 2:1 aspect ratio required for equirectangular images:

In the UI: Output Tab → Output Resolution (dropdown + manual input)

Tile Resolution Controls

Located in the Hextile Tab, these control how tiles are extracted and stitched:

Tile Input Resolution

Size at which tiles are extracted from the equirectangular image and sent to the diffusion model.

Tile Output Resolution

Size at which processed tiles are resized before stitching back into the equirectangular image.

• Typically matches Tile Input Resolution
• Can be increased for upscaling effect (e.g., input 512 → output 1024)
• Uses LANCZOS resampling for quality

Model-Sensitive Tile Sizes

The UI shows model-specific native tile sizes: - SDXL 1.0: 1024×1024 (native) - SDXL-Turbo: 512×512 (native) - SD3.5 Turbo/Large: 1024×1024 (native) - Qwen-Image / TeleStyle: 1024×1024 (native)

Tip: Using non-native tile sizes shows a warning. Processing still works but may produce different results.

Example Configurations

Standard Quality (Default):

{
  "hextile": {
    "template": "Hextile_44_4K",
    "tile_input_width": 1024,
    "tile_input_height": 1024,
    "tile_output_width": 1024,
    "tile_output_height": 1024
  },
  "output": {
    "width": 8192,
    "height": 4096
  }
}

SDXL-Turbo with Native 512 Tiles:

{
  "pipeline": "sdxl_inpaint",
  "model": "local/sdxl-turbo",
  "hextile": {
    "tile_input_width": 512,
    "tile_input_height": 512,
    "tile_output_width": 512,
    "tile_output_height": 512
  }
}

Tile Upscaling (input small, output larger):

{
  "hextile": {
    "tile_input_width": 512,
    "tile_input_height": 512,
    "tile_output_width": 1024,
    "tile_output_height": 1024
  }
}

VRAM Considerations

If encountering OOM errors: Try reducing tile input size to 512×512 with a compatible model.

Cardinal Prompt System

Available for all diffusion pipelines.

How It Works

Global Prompt: "fantasy landscape"

Cardinal Prompts:
├─ Front: "enchanted forest entrance"
├─ Right: "ancient stone bridge"
├─ Back: "mystical mountain peaks"
├─ Left: "crystal clear lake"
├─ Above: "starry night sky"
└─ Below: "mossy forest floor"

Result: Each tile gets interpolated prompt based on viewing direction

Interpolation Modes

None (Global Only): - All tiles use same prompt - Uniform look across 360° - Simpler, more predictable

6 Cardinal Directions (Recommended): - Smooth transitions between directions - More natural 360° scenes - Takes advantage of hextile geometry

LoRA Support

Available for SD 1.5, SD 2.1, SD 3.5, and SDXL pipelines. TeleStyle has a built-in style LoRA. Qwen-Image does not use LoRAs.

LoRA Directories

Each pipeline family uses its own LoRA directory:

Using LoRAs

1. Place .safetensors files in the appropriate directory for your pipeline
2. Select the pipeline in the UI
3. Navigate to the LoRA tab
4. Click "Add LoRA"
5. Choose model and set strength (0.0-1.0)
6. Add multiple LoRAs (they stack)

Combine Modes

• Additive (default): Each LoRA strength is applied independently
• Normalized: LoRA weights are normalized to sum to 1.0

Tips

• Start with strength 0.5-0.7
• Too high strength can overwhelm prompts
• Use only compatible LoRAs (SDXL LoRAs for SDXL, etc.)
• SD 1.5 has the largest LoRA ecosystem
• System lists available LoRAs via API

Config Files

Pipeline selection is saved in config files:

{
  "pipeline": "qwen_image",  ← Saved with config!
  "hextile": { ... },
  "diffusion": { ... },
  "output": { ... }
}

Loading Configs: - Config file includes pipeline - System automatically switches to saved pipeline - UI updates to show correct form - All settings restored

Pipeline Management

The Pipeline Management page lets you install, repair, and manage AI models.

Accessing Pipeline Management

Navigate to Pipelines in the main navigation menu, or click the gear icon next to the pipeline dropdown.

Pipeline Status

Each pipeline shows its current status:

Installing Pipelines

1. Click Install on any uninstalled pipeline
2. For gated models (SD 3.5, Qwen-Image), authenticate first:
3. Click Authenticate with HuggingFace
4. Enter your access token
5. Wait for validation
6. Monitor download progress via the progress bar
7. Once complete, the pipeline is ready to use

Download Sizes

Repair/Reinstall

If a pipeline isn't working correctly: 1. Click Repair to validate and fix the installation 2. If repair fails, click Uninstall then Install again

Health Check

Click Validate to run a health check on any installed pipeline. This verifies: - Model files are present and complete - Configuration is valid - Pipeline can be loaded

Test Render

Click Test to run a quick test render with default settings. This confirms the pipeline works end-to-end.

Performance Tips

VRAM Optimization

If OOM (Out of Memory) Errors: 1. Switch from batch to sequential mode 2. Use smaller template (Hextile_20_2K vs 44_4K) 3. Reduce inference steps 4. Lower output resolution 5. For Qwen-Image BF16: Switch to GGUF Q4 variant (13GB vs 48GB)

Speed Optimization

Fastest Processing: 1. Use smaller templates for previews 2. Reduce inference steps (but watch quality) 3. Use smaller templates 4. Use FLUX.1 Schnell for ultra-fast 4-step generation

Quality Optimization

Best Quality: 1. Use Hextile_44_4K template 2. Increase inference steps (70-100 SDXL, 40-50 Qwen-Image) 3. Use sequential mode (better tile blending) 4. Adjust strength carefully 5. Use cardinal prompts for better 360° coherence

Troubleshooting

"CUDA Out of Memory"

Solution: - Switch to sequential processing mode - Restart application (clears VRAM leaks) - Close other GPU applications - Use smaller template - Reduce batch size

"Pipeline Not Found"

Solution: - Check backend startup logs - Verify processors registered correctly - Restart backend server

"Model Loading Failed"

Solution: - Check model path in config - Verify HuggingFace model ID - Ensure internet connection (for downloading) - Check disk space for model cache

Tiles Don't Blend Well

Solution: - Use sequential mode (better blending) - Increase inference steps - Adjust strength (try lower values) - Use cardinal prompts for consistency - Ensure template is correct

Next Steps

• Getting Started - First render walkthrough
• Templates - Understanding hexagonal templates
• Format Converter - Projection format conversion
• API Reference - Programmatic access
• Architecture - How the system works

Ready to start? Try your first render →

See also: - ControlNet Guide - Using ControlNet for structural guidance - Settings - Application settings and HuggingFace authentication

Last Updated: 2026-03-13 | V3.0 Pipeline Guide