[diffusion] model: support two stage pipeline of LTX-2 (#20707)
Co-authored-by: daiweitao <dwti614707404@163.com> Co-authored-by: Mick <mickjagger19@icloud.com> Co-authored-by: GMI Xiao Jin <xiao.j@gmicloud.ai>
This commit is contained in:
co-authored by
daiweitao
Mick
GMI Xiao Jin
parent
95cdbce34f
commit
db3d4f4b76
@@ -1,156 +1,156 @@
|
||||
{
|
||||
"_comment": "Per-model comparison config. Only frameworks listed under each case are tested. vLLM-Omni disabled until dep install issues resolved.",
|
||||
"test_image_url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png",
|
||||
"cases": [
|
||||
{
|
||||
"id": "flux1_dev_t2i_1024",
|
||||
"model": "black-forest-labs/FLUX.1-dev",
|
||||
"task": "text-to-image",
|
||||
"prompt": "A futuristic cyberpunk city at night, neon lights reflecting on wet streets",
|
||||
"width": 1024,
|
||||
"height": 1024,
|
||||
"num_inference_steps": 50,
|
||||
"guidance_scale": 4.0,
|
||||
"seed": 42,
|
||||
"num_gpus": 1,
|
||||
"frameworks": {
|
||||
"sglang": {
|
||||
"serve_args": "--enable-torch-compile --warmup --dit-layerwise-offload false",
|
||||
"extra_env": {}
|
||||
"_comment": "Per-model comparison config. Only frameworks listed under each case are tested. vLLM-Omni disabled until dep install issues resolved.",
|
||||
"test_image_url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png",
|
||||
"cases": [
|
||||
{
|
||||
"id": "flux1_dev_t2i_1024",
|
||||
"model": "black-forest-labs/FLUX.1-dev",
|
||||
"task": "text-to-image",
|
||||
"prompt": "A futuristic cyberpunk city at night, neon lights reflecting on wet streets",
|
||||
"width": 1024,
|
||||
"height": 1024,
|
||||
"num_inference_steps": 50,
|
||||
"guidance_scale": 4.0,
|
||||
"seed": 42,
|
||||
"num_gpus": 1,
|
||||
"frameworks": {
|
||||
"sglang": {
|
||||
"serve_args": "--enable-torch-compile --warmup --dit-layerwise-offload false",
|
||||
"extra_env": {}
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "flux2_dev_t2i_1024",
|
||||
"model": "black-forest-labs/FLUX.2-dev",
|
||||
"task": "text-to-image",
|
||||
"prompt": "A futuristic cyberpunk city at night, neon lights reflecting on wet streets",
|
||||
"width": 1024,
|
||||
"height": 1024,
|
||||
"num_inference_steps": 50,
|
||||
"guidance_scale": 4.0,
|
||||
"seed": 42,
|
||||
"num_gpus": 1,
|
||||
"frameworks": {
|
||||
"sglang": {
|
||||
"serve_args": "--enable-torch-compile --warmup --dit-layerwise-offload false",
|
||||
"extra_env": {}
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "qwen_image_2512_t2i_1024",
|
||||
"model": "Qwen/Qwen-Image-2512",
|
||||
"task": "text-to-image",
|
||||
"prompt": "A futuristic cyberpunk city at night, neon lights reflecting on wet streets",
|
||||
"width": 1024,
|
||||
"height": 1024,
|
||||
"num_inference_steps": 50,
|
||||
"guidance_scale": 4.0,
|
||||
"seed": 42,
|
||||
"num_gpus": 1,
|
||||
"frameworks": {
|
||||
"sglang": {
|
||||
"serve_args": "--enable-torch-compile --warmup",
|
||||
"extra_env": {}
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "qwen_image_edit_2511",
|
||||
"model": "Qwen/Qwen-Image-Edit-2511",
|
||||
"task": "image-edit",
|
||||
"prompt": "Make the cat wear a red hat",
|
||||
"reference_image": true,
|
||||
"width": 1024,
|
||||
"height": 1024,
|
||||
"num_inference_steps": 50,
|
||||
"guidance_scale": 4.0,
|
||||
"seed": 42,
|
||||
"num_gpus": 1,
|
||||
"frameworks": {
|
||||
"sglang": {
|
||||
"serve_args": "--enable-torch-compile --warmup",
|
||||
"extra_env": {}
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "zimage_turbo_t2i_1024",
|
||||
"model": "Tongyi-MAI/Z-Image-Turbo",
|
||||
"task": "text-to-image",
|
||||
"prompt": "A futuristic cyberpunk city at night, neon lights reflecting on wet streets",
|
||||
"width": 1024,
|
||||
"height": 1024,
|
||||
"num_inference_steps": 9,
|
||||
"guidance_scale": 4.0,
|
||||
"seed": 42,
|
||||
"num_gpus": 1,
|
||||
"frameworks": {
|
||||
"sglang": {
|
||||
"serve_args": "--enable-torch-compile --warmup",
|
||||
"extra_env": {}
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "wan22_t2v_a14b_720p",
|
||||
"model": "Wan-AI/Wan2.2-T2V-A14B-Diffusers",
|
||||
"task": "text-to-video",
|
||||
"prompt": "A cat and a dog baking a cake together in a kitchen.",
|
||||
"width": 1280,
|
||||
"height": 720,
|
||||
"num_frames": 81,
|
||||
"num_inference_steps": 2,
|
||||
"guidance_scale": 5.0,
|
||||
"seed": 42,
|
||||
"num_gpus": 4,
|
||||
"frameworks": {
|
||||
"sglang": {
|
||||
"serve_args": "--enable-torch-compile --warmup --enable-cfg-parallel --ulysses-degree 2 --text-encoder-cpu-offload --pin-cpu-memory",
|
||||
"extra_env": {}
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "wan22_ti2v_5b_720p",
|
||||
"model": "Wan-AI/Wan2.2-TI2V-5B-Diffusers",
|
||||
"task": "text-image-to-video",
|
||||
"prompt": "The cat starts walking slowly towards the camera.",
|
||||
"reference_image": true,
|
||||
"width": 1280,
|
||||
"height": 720,
|
||||
"num_frames": 81,
|
||||
"num_inference_steps": 50,
|
||||
"guidance_scale": 5.0,
|
||||
"seed": 42,
|
||||
"num_gpus": 1,
|
||||
"frameworks": {
|
||||
"sglang": {
|
||||
"serve_args": "--enable-torch-compile --warmup",
|
||||
"extra_env": {}
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "wan22_i2v_a14b_720p",
|
||||
"model": "Wan-AI/Wan2.2-I2V-A14B-Diffusers",
|
||||
"task": "image-to-video",
|
||||
"prompt": "The cat starts walking slowly towards the camera.",
|
||||
"reference_image": true,
|
||||
"width": 1280,
|
||||
"height": 720,
|
||||
"num_frames": 81,
|
||||
"num_inference_steps": 2,
|
||||
"guidance_scale": 5.0,
|
||||
"seed": 42,
|
||||
"num_gpus": 4,
|
||||
"frameworks": {
|
||||
"sglang": {
|
||||
"serve_args": "--enable-torch-compile --warmup --enable-cfg-parallel --ulysses-degree 2 --text-encoder-cpu-offload --pin-cpu-memory",
|
||||
"extra_env": {}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "flux2_dev_t2i_1024",
|
||||
"model": "black-forest-labs/FLUX.2-dev",
|
||||
"task": "text-to-image",
|
||||
"prompt": "A futuristic cyberpunk city at night, neon lights reflecting on wet streets",
|
||||
"width": 1024,
|
||||
"height": 1024,
|
||||
"num_inference_steps": 50,
|
||||
"guidance_scale": 4.0,
|
||||
"seed": 42,
|
||||
"num_gpus": 1,
|
||||
"frameworks": {
|
||||
"sglang": {
|
||||
"serve_args": "--enable-torch-compile --warmup --dit-layerwise-offload false",
|
||||
"extra_env": {}
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "qwen_image_2512_t2i_1024",
|
||||
"model": "Qwen/Qwen-Image-2512",
|
||||
"task": "text-to-image",
|
||||
"prompt": "A futuristic cyberpunk city at night, neon lights reflecting on wet streets",
|
||||
"width": 1024,
|
||||
"height": 1024,
|
||||
"num_inference_steps": 50,
|
||||
"guidance_scale": 4.0,
|
||||
"seed": 42,
|
||||
"num_gpus": 1,
|
||||
"frameworks": {
|
||||
"sglang": {
|
||||
"serve_args": "--enable-torch-compile --warmup",
|
||||
"extra_env": {}
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "qwen_image_edit_2511",
|
||||
"model": "Qwen/Qwen-Image-Edit-2511",
|
||||
"task": "image-edit",
|
||||
"prompt": "Make the cat wear a red hat",
|
||||
"reference_image": true,
|
||||
"width": 1024,
|
||||
"height": 1024,
|
||||
"num_inference_steps": 50,
|
||||
"guidance_scale": 4.0,
|
||||
"seed": 42,
|
||||
"num_gpus": 1,
|
||||
"frameworks": {
|
||||
"sglang": {
|
||||
"serve_args": "--enable-torch-compile --warmup",
|
||||
"extra_env": {}
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "zimage_turbo_t2i_1024",
|
||||
"model": "Tongyi-MAI/Z-Image-Turbo",
|
||||
"task": "text-to-image",
|
||||
"prompt": "A futuristic cyberpunk city at night, neon lights reflecting on wet streets",
|
||||
"width": 1024,
|
||||
"height": 1024,
|
||||
"num_inference_steps": 9,
|
||||
"guidance_scale": 4.0,
|
||||
"seed": 42,
|
||||
"num_gpus": 1,
|
||||
"frameworks": {
|
||||
"sglang": {
|
||||
"serve_args": "--enable-torch-compile --warmup",
|
||||
"extra_env": {}
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "wan22_t2v_a14b_720p",
|
||||
"model": "Wan-AI/Wan2.2-T2V-A14B-Diffusers",
|
||||
"task": "text-to-video",
|
||||
"prompt": "A cat and a dog baking a cake together in a kitchen.",
|
||||
"width": 1280,
|
||||
"height": 720,
|
||||
"num_frames": 81,
|
||||
"num_inference_steps": 2,
|
||||
"guidance_scale": 5.0,
|
||||
"seed": 42,
|
||||
"num_gpus": 4,
|
||||
"frameworks": {
|
||||
"sglang": {
|
||||
"serve_args": "--enable-torch-compile --warmup --enable-cfg-parallel --ulysses-degree 2 --text-encoder-cpu-offload --pin-cpu-memory",
|
||||
"extra_env": {}
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "wan22_ti2v_5b_720p",
|
||||
"model": "Wan-AI/Wan2.2-TI2V-5B-Diffusers",
|
||||
"task": "text-image-to-video",
|
||||
"prompt": "The cat starts walking slowly towards the camera.",
|
||||
"reference_image": true,
|
||||
"width": 1280,
|
||||
"height": 720,
|
||||
"num_frames": 81,
|
||||
"num_inference_steps": 50,
|
||||
"guidance_scale": 5.0,
|
||||
"seed": 42,
|
||||
"num_gpus": 1,
|
||||
"frameworks": {
|
||||
"sglang": {
|
||||
"serve_args": "--enable-torch-compile --warmup",
|
||||
"extra_env": {}
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "wan22_i2v_a14b_720p",
|
||||
"model": "Wan-AI/Wan2.2-I2V-A14B-Diffusers",
|
||||
"task": "image-to-video",
|
||||
"prompt": "The cat starts walking slowly towards the camera.",
|
||||
"reference_image": true,
|
||||
"width": 1280,
|
||||
"height": 720,
|
||||
"num_frames": 81,
|
||||
"num_inference_steps": 2,
|
||||
"guidance_scale": 5.0,
|
||||
"seed": 42,
|
||||
"num_gpus": 4,
|
||||
"frameworks": {
|
||||
"sglang": {
|
||||
"serve_args": "--enable-torch-compile --warmup --enable-cfg-parallel --ulysses-degree 2 --text-encoder-cpu-offload --pin-cpu-memory",
|
||||
"extra_env": {}
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user