🎨 QWEN-Anime | Beta3-AIO

⚠️ Note: All versions are combined on this model card for convenience.

🎨 VERSION 3 MAJOR UPDATE

NEW FEATURES:

- Image Editing functionality added (1-3 images)

- Upgraded base: Qwen Image Edit 2511 (from 2509)

- Faster generation: 4 steps minimum (down from 8)

- Custom Qwen 2.5 VL 7B FP8 uncut for maximum creative freedom

- Supports both Text-to-Image and Image-to-Image workflows

- ???? capabilities: Partial ?????? and clothing removal possible

- Results depend on seed, prompt, and input images

- Tip: Load ???? image as second image for better results

- FP8 only (other formats on request)

From pure text generation to advanced image editing!

🧠 Available Versions

💎 Anime Beta3 (All-in-One) - NEW! ⭐

🎉 No separate VAE/Text Encoder needed - just load and go!

🟡 Pruned Model fp8 (26.99 GB) = 4-8 steps version, CFG 1.0 (optimized for speed)

💎 Beta2-AIO (All-in-One)

🎉 No separate VAE/Text Encoder needed - just load and go!

🟢 Full Model fp8 (26.99 GB) = 20+ steps version, normal CFG (2.5-4.0)
🟡 Pruned Model fp8 (26.99 GB) = 6-8 steps version, CFG 1.0 (optimized for speed)

Key Features:

• ✅ Integrated VAE + Text Encoder

• ✅ Single file, plug-and-play

• ✅ Use regular "Load Checkpoint" node

• ✅ Same Beta2 quality, easier setup

🧠 Beta2 (Safetensors & GGUF)

Requires separate VAE + Text Encoder

⚠️ Note: Unfortunately, I had to use some tricks to make all versions fit on one model card.

🧠 SafeTensor Versions

🟪 BF16 = Pruned Model bf16 (38.05 GB)
🟦 FP16 = Pruned Model fp16 (38.05 GB)
🟨 FP8 = Pruned Model fp8 (19.03 GB)

💾 GGUF Versions

⚠️ Requires ComfyUI-GGUF: https://github.com/city96/ComfyUI-GGUF

🔹 F16 = Full Model fp16 (38.07 GB)
🔹 Q8 = Full Model fp8 (20.23 GB)
🔹 Q6_K = Full Model bf16 (15.63 GB)
🔹 Q4_K_S = Full Model nf4 (10.72 GB)

💡 Quick Guide:

• Safetensors (🟪🟦🟨) → Use regular "Load Diffusion Model" node

• GGUF (🔹) → Needs ComfyUI-GGUF → "GGUF Loader" node + unet/ folder

📦 Beta1 (Legacy)

• FP16 only (38.05 GB)

• Requires separate VAE + Text Encoder

📊Example image editing, Beta3-AIO:

Tested on Nvidia RTX 4060 with Euler sampler

Prompt:

Place the two figures in a fantasy medieval tavern, laughing and clinking two beer glasses.

📊 Beta2-AIO Test Results

Tested on Nvidia RTX 4060 with Euler A sampler

🟢 Full Model fp8 (20+ Steps Version)

Test 1: Elegant Shrine Maiden

Resolution: 1024×1024 | Steps: 24 | CFG: 3.6 | Time: ~176.48s

Prompt:

anime, masterpiece, best quality, 1girl, shrine maiden, long black hair, 
red hakama, white kimono top, holding paper talisman, sacred shrine background, 
cherry blossoms falling, soft sunlight, detailed face, serene expression, 
traditional japanese architecture, torii gate in background, 
cinematic lighting, depth of field

Test 2: Cyberpunk Street Scene

Resolution: 1536×1024 | Steps: 28 | CFG: 4.0 | Time: ~229.52s

Prompt:

anime, 2k quality, ultra-detailed, 1girl, cyberpunk hacker, 
neon-lit tokyo street, rain reflections, holographic advertisements, 
purple and cyan color scheme, tech wear jacket, mechanical arm augmentation, 
confident pose, sharp focus, cinematic composition, bokeh background, 
night city atmosphere, detailed eyes

Test 3: Fantasy Dragon Knight

Resolution: 832×1216 | Steps: 32 | CFG: 3.8 | Time: ~227.94s

Prompt:

anime, masterpiece, high detail, 1girl, dragon knight, 
silver armor with blue accents, flowing cape, dragon companion beside her, 
epic fantasy landscape, castle ruins background, dramatic sky, 
wind effect on hair and cape, detailed armor patterns, 
heroic pose, cinematic lighting, depth of field

🟡 Pruned Model fp8 (6-8 Steps Version)

Test 4: Cozy Cafe Moment

Resolution: 1024×1024 | Steps: 8 | CFG: 1.0 | Time: ~32.47s

Prompt:

anime, best quality, 1girl, casual outfit, sitting in cafe, 
holding coffee cup, warm lighting, bokeh background, 
soft smile, detailed eyes, cozy atmosphere, 
window light, autumn colors, relaxed pose

Test 5: Magical Girl Transformation

Resolution: 512×768 | Steps: 7 | CFG: 1.0 | Time: ~19.28s

Prompt:

anime, masterpiece, 1girl, magical girl, transformation pose, 
sparkles and light effects, flowing hair, colorful costume, 
magic circle background, dynamic composition, 
vibrant colors, detailed ribbons, glowing effects

Test 6: Beach Sunset Portrait

Resolution: 1024×1536 | Steps: 6 | CFG: 1.0 | Time: ~32.07s

Prompt:

anime, best quality, 1girl, summer dress, beach sunset, 
golden hour lighting, ocean waves, soft wind effect on hair, 
warm colors, peaceful expression, detailed face, 
cinematic sunset, depth of field, romantic atmosphere

🎯 Quick Settings Guide

🟢 Full Model fp8 (Quality Mode):

• Steps: 20-32

• CFG: 2.5-4.0 (sweet spot: 3.6)

• Sampler: Euler A, Euler Normal, Beta, Simple

• Use for: High quality, detailed work, final renders

🟡 Pruned Model fp8 (Speed Mode):

• Steps: 6-8 (optimal: 8)

• CFG: 1.0 (can go to 2.0 max, but stay at 1.0)

• Sampler: Euler A recommended

• Use for: Fast iterations, testing, quick generations

Both Versions:

• Resolution: 512×512 to 2048×1152

• VRAM: 8GB+ recommended

• Lightning LoRAs: Compatible (4-step or 8-step)

🔧 Installation Guide

Beta2-AIO (Easiest!):

1. Download your preferred version (Full or Pruned)

2. Place in ComfyUI/models/checkpoints/

3. Load with standard "Load Checkpoint" node

4. Generate! No extra files needed!

Beta2 (Safetensors):

1. Download checkpoint → diffusion_models/

2. Download Text Encoder → text_encoders/QWEN/

3. Download VAE → vae/QWEN/

4. Use "Load Diffusion Model" node

Beta2 (GGUF):

1. Install ComfyUI-GGUF

2. Download GGUF → unet/

3. Download Text Encoder + VAE (same as above)

4. Use "GGUF Loader" node

💡 Which Version Should I Choose?

Choose Beta2-AIO (Pruned) if:

✅ Want fastest generations (6-8 steps)
✅ Need quick iterations/testing
✅ Prefer simplicity (single file)
✅ 8GB+ VRAM available

Choose Beta2-AIO (Full) if:

✅ Want maximum quality
✅ Need more control (CFG 2.5-4.0)
✅ Creating final/detailed work
✅ Prefer traditional workflow

Choose Beta2 FP8 if:

✅ Want flexibility (separate VAE/encoder)
✅ Using custom VAE/encoders
✅ Need maximum compatibility

Choose Beta2 GGUF if:

✅ Limited VRAM (6-8GB)
✅ Want smallest files (Q4 = 10GB)
✅ CPU inference needed

Choose Beta1 if:

✅ Compatibility with old workflows
✅ Testing/comparison purposes

📝 Prompting Tips

Quality Tags (All Versions):

anime, masterpiece, best quality, ultra-detailed, 
2k resolution, sharp focus, cinematic lighting

Style Modifiers:

MOE STYLE, official art, anime coloring, 
detailed eyes, depth of field, bokeh

Negative Prompt:

low quality, blurry, bad ???????, bad hands, 
text, watermark, mutation, distorted

⚙️ Technical Specs

Feature Beta2-AIO Beta2 Beta1 Setup Single file 4 files 4 files VAE Integrated Separate Separate Text Encoder Integrated Separate Separate File Size 20.5 GB 19-38 GB 38 GB Speed (8 steps) ⚡⚡⚡ ⚡⚡ ⚡ Quality Same as Beta2 Excellent Good Training Extended Extended Base

🔞 Content Notice

Limited NSFW: ??????????????? (breasts/underboob) supported
Not Supported: Full ???????? content
Age: 18+ only, use responsibly

❓ FAQ

Q: Which AIO version should I use?
A: Pruned for speed (6-8 steps), Full for quality (20+ steps).

Q: Can I use Lightning LoRAs with AIO?
A: Yes! Both AIO versions support Lightning LoRAs.

Q: Do I need separate VAE/encoder for AIO?
A: No! AIO has everything integrated.

Q: What's the difference between Full and Pruned AIO?
A: Full = quality mode (CFG 2.5-4.0, 20+ steps). Pruned = speed mode (CFG 1.0, 6-8 steps).

Q: Why does Pruned need CFG 1.0?
A: It's optimized for low-step high-speed generation. CFG 1.0 works best.

Q: Can I use CFG 3.0 with Pruned?
A: Not recommended. Max is 2.0, but results are best at 1.0.

Q: Is quality different between AIO and Beta2 FP8?
A: No, same training - AIO just bundles files together.

Q: Which has better quality: Full AIO or Beta2 BF16?
A: Beta2 BF16 has slightly better precision, but difference is minimal.

🙏 Credits

Training: Custom dataset, Dual Tesla P40 GPUs
Base: qwen-image-edit 2509
Community: Thanks to all Beta1 & Beta2 testers!

🚀 Download & Start Creating!

1. Choose your version (AIO recommended for beginners)

2. Download from files section

3. Place in correct folder

4. Load in ComfyUI

5. Generate amazing anime art!

Version: Beta1, Beta2, Beta2-AIO
Release: November 2025
License: Apache 2.0

Created with ❤️ for the anime AI community