Sulphur 2
Frontierby SulphurAI
Sulphur 2 (base) is a 9B uncensored video generation model built on the LTX-2.3 architecture, supporting native text-to-video and image-to-video. Ships with a built-in prompt enhancer and quantized GGUF builds (~9.5GB Q8_0) for consumer hardware.
- 9B uncensored video model built on the LTX-2.3 architecture
- Native text-to-video and image-to-video with a built-in prompt enhancer
- GGUF Q8_0 builds (~9.5GB) for consumer GPUs
- Integrated into ~30 community ComfyUI spaces
Your hardware
Detecting...
Image Quality Benchmarks
Measured quality metrics for Sulphur 2 outputs.
How often humans prefer this model's output (0-100%)
Visual quality and composition rating (5-9 scale)
VRAM by Scenario
VRAM estimates at FP16 and FP8 precision. FP8 uses ~40% less memory with minimal quality loss. Grade shows how well each GPU handles the generation workload.
FP16 (full precision)
| Scenario | VRAM | RTX 4090 24GB | RTX 3060 12GB | RTX 4060 8GB | MacBook Pro M4 Pro 24GB |
|---|---|---|---|---|---|
| 512×512 · 25 frames | 34.5 GB | F | F | F | F |
| 768×512 · 25 frames | 36.6 GB | F | F | F | F |
| 768×512 · 100 frames | 42.9 GB | F | F | F | F |
| 1280×720 · 25 frames | 45.1 GB | F | F | F | F |
FP8 (quantized — ~40% less VRAM)
| Scenario | VRAM | RTX 4090 24GB | RTX 3060 12GB | RTX 4060 8GB | MacBook Pro M4 Pro 24GB |
|---|---|---|---|---|---|
| 512×512 · 25 frames | 20.2 GB | A | F | F | D |
| 768×512 · 25 frames | 22.3 GB | B | F | F | D |
| 768×512 · 100 frames | 28.6 GB | D | F | F | F |
| 1280×720 · 25 frames | 30.7 GB | D | F | F | F |
Optimization Tips
GGUF Q4 available
Quantized GGUF format for lower VRAM and smaller downloads
Run with Python
from diffusers import LTXConditionPipeline
import torch
pipe = LTXConditionPipeline.from_pretrained(
"SulphurAI/Sulphur-2-base",
torch_dtype=torch.bfloat16
)
pipe.to("cuda")
frames = pipe(
prompt="your prompt here",
num_inference_steps=8,
guidance_scale=1.0,
num_frames=121,
).frames[0]
# Save frames or export as videoGet started
Setup instructions for running Sulphur 2 locally
1. Download the model
Get the checkpoint from HuggingFace
2. Place in:
ComfyUI/models/checkpoints/ (or ComfyUI/models/unet/ for GGUF)3. Launch ComfyUI
python main.pyMemory Breakdown
VRAM allocation for 25 frames at 768×512 on RTX 4090 24GB
Estimated Generation Time
25 frames at 768×512, 30 steps, FP16.
Available Formats & Downloads
Download Sulphur 2 in different precisions. Lower precision = less VRAM but slight quality loss.
LoRA Ecosystem
LimitedNew model with an emerging LoRA ecosystem.
Related Workflows
You might also like
Frequently asked questions
FAQ — Sulphur 2
How much VRAM does Sulphur 2 need for video?
Sulphur 2 (9B parameters) requires approximately 36.6 GB of VRAM at FP16 precision for generating 25 frames at 768×512. Video generation typically requires more VRAM than image generation due to temporal attention layers.
Can I run Sulphur 2 on RTX 4090?
Sulphur 2 exceeds the RTX 4090's 24 GB VRAM at FP16 for video generation. Consider reducing resolution, frame count, or using a GPU with more VRAM.
How long does it take to generate a video with Sulphur 2?
On a reference GPU (RTX 4090 24GB), Sulphur 2 generates a 25-frame video at 768×512 in approximately ~2m 38s at FP16 with 30 inference steps. Faster GPUs with higher memory bandwidth will reduce generation time.
What resolution and frame count does Sulphur 2 support?
Sulphur 2 supports up to 1280×720 resolution and 241 frames per generation at 30 FPS. Higher resolutions and frame counts require proportionally more VRAM.
About Sulphur 2
See also