CogVideoX-2B
Free.ai (self-hosted)
·
video
·
~30000 Ama-token ngalinye video clip
·
3.2
kusuka 87 Abasebenzisi balolu hlu
CogVideoX-2B yi an imodeli yokukhiqiza ividiyo eyenziwe ngu Tsinghua University. Onamandla kakhulu ku-Short video clips from text. I-self-hosted ku-Free.ai GPUs - isebenza ngokukhululekile ngaphezu kwe-token pool yakho yansuku zonke (30,000 tokens i-clip ngayinye ~5s). Kukhishwa ngaphansi kwe-Apache 2.0 - ukusetshenziswa kokuthengiswayo kuvunyelwe ku-Free.ai.
Sebenzisa nge-API
I-REST API ehambisana ne-OpenAI. Dala isithonjana bese ubiza le modeli emaminithini.
curl -X POST https://api.free.ai/v1/video/generate/ \
-H "Authorization: Bearer sk-free-..." \
-H "Content-Type: application/json" \
-d '{"model":"cogvideox","prompt":"your prompt here"}'Amamodeli afana
Imibuzo ebuzwa kaningi
CogVideoX-2B yiyona imodeli yevidiyo ye-AI etholakala ku-Free.ai. Sebenzisa ifomu kule khasi ukudala i-clip; ngaphansi kwe-fold uzothola i-sample prompts, i-price, ne-alternatives.
Ku-Free.ai, ukukhishwa kwevidiyo kufinyelela kumasekondi angama-6 ngeclip ngayinye kuzo zonke imodeli yevidiyo. Ukudlulisa, sebenzisa inkinobho yokudlulisa kuhele /video/ tool - ithatha ifreyimu yokugqibela futhi iqhubeka khona.
16:9 landscape (YouTube, desktop), 9:16 portrait (TikTok, Reels, Shorts), and 1:1 square (Instagram feed). Khetha isilinganiso kwifomu ngaphambi kokwenza ngakho imodeli ifaka isithombe sobuso bobuso.
720p HD ngokuzenzakalela. Ezinye izimodeli eziphezulu zixhasa kuze kube yi-1080p - hlola ikhadi lokuqhathaniswa. Ungakhuphula noma yisiphi isingeniso /video/upscaler/ ngemuva kokwenza.
Kunamandla ku-natural movement (abantu behamba, izimoto zihamba, amanzi, isimo sezulu). Kuncane ku-involvement yesandla esinzima kanye nobhalo oluhle. Sebenzisa ama-camera-direction hints (slow pan, dolly forward) uku-clean movement.
Free.ai inikeza ukusetshenziswa komphakathi kwevidiyo ekhiqizwe kuwe kungakhathaliseki imodeli. Imodeli ngokwayo ingabe yi Apache 2.0, MIT, noma ilayisense elikhethekile lomthengisi - bona i-link yokubhekisa kwemodeli ngezansi.
CogVideoX-2B runs on our own GPUs at 30,000 tokens per clip, flat: a render costs what it costs because of model load and diffusion steps, not clip length, and 2,500 per second only takes over past 12 seconds. That is the entire 30,000-token daily free pool, so a free account gets one clip every two days. Paid token packs start at $5 → 200,000 tokens and remove the cap.
Yebo - sebenzisa /batch/ kuze kube yi-100. I-clip ngayinye ibekwe eqenjini futhi imiphumela iwela ku /account/?tab=history uma ilungile.
Yebo - UTHENGA umlayezo wakho ku /v1/video/generate/ ngemodeli "CogVideoX-2B" (noma sebenzisa i-slug kulekhasi). Bona /api/ ukubheka indawo yokuqeda egcwele kanye nokuqinisekisa, amakhodi wephutha, ne-SDK snippets.
Sigcina izicelo zakho ngaphandle kwefasitela lokuhlelwa (24h anon, 7d ukungena). Sizoqeqesha ngemingeniso yakho. Amamodeli ahlala asebenza nge-Free.ai-owned GPUs.
Yebo - imisebenzi engaphumelelanga ibuyiselwa ngokuzenzakalela emthonjeni wokhokha oyinhloko (i-pool yansuku zonke noma ama-token akhokhelwe) ngosuku olufanayo. I-imeyili contact@free.ai uma ukubuyiselwa akubonisi.
Ukwenza okujwayelekile 30-120 imizuzwana yevidiyo yemizuzu engu-4; amamodeli aphezulu avame ukuqedwa emizuzwani engu-15-45. Sebenzisa inkinobho yokuvala-i-tab-ephephile ye-queue ku /video/ - imiphumela yakho iwela ku /account/?tab=history uma yenziwe, nge-imeyili ekhethiwe.