QWEN HYPER REALISM
5.0
0 reviews
Description
QWEN LORA LOADER: https://github.com/Cx330v/Qwen-Image-Toolkit
QWEN REALISM LORAS ARE OUT: and just 15 steps
cfg: 2.0
sampler: res_2m
scheduler: bong_tangent
shift: 7:00
resolution: 1328x928
Prompt executed in 153.95 seconds on an RTX 560 ti 16GB and 64GB system Ram.
You may halve the execution time by lowering CFG to 1.0 but with small details loss.
MODELS:
QWEN-IMAGE FP8 https://huggingface.co/.../qwen_image_fp8_e4m3fn.safetensors
TEXT ENCODER FP16 or FPH https://huggingface.co/.../qwen_2.5_vl_7b_fp8_scaled...
VAE https://huggingface.co/.../vae/qwen_image_vae.safetensors
REALISM LORA: https://huggingface.co/flymy-ai/qwen-image-lora/blob/main/pytorch_lora_weights.safetensors download and rename.
5
Discussion
(No comments yet)
Loading...
Reviews
No reviews yet
Versions (1)
- latest (a month ago)
Node Details
Primitive Nodes (11)
EmptySD3LatentImage (3)
Fast Groups Bypasser (rgthree) (1)
LayerUtility: Gemini (1)
ModelSamplingAuraFlow (1)
Note (3)
QwenImageLoraLoader (2)
Custom Nodes (19)
- CR Text Input Switch (1)
ComfyUI
- UNETLoader (1)
- CLIPLoader (1)
- VAELoader (1)
- SaveImage (1)
- VAEDecode (1)
- KSampler (1)
- LoadImage (1)
- CLIPTextEncode (2)
- easy promptReplace (1)
- easy positive (3)
- easy showAnything (2)
- Latent Switch (JPS) (1)
- SaveText|pysssss (1)
- Text Concatenate (1)
Model Details
Checkpoints (0)
LoRAs (2)
QWEN/flymy_realism.safetensors
QWEN/valentin_realism_qwen.safetensors